Merge branch 'AUTOMATIC1111:master' into limit-extra-tab-preivew-buttons

configs/instruct-pix2pix.yaml

@@ -20,8 +20,7 @@ model:
     conditioning_key: hybrid
     monitor: val/loss_simple_ema
     scale_factor: 0.18215
-    use_ema: true
+    use_ema: false
-    load_ema: true
 
     scheduler_config: # 10000 warmup steps
       target: ldm.lr_scheduler.LambdaLinearScheduler

javascript/hints.js

@@ -17,7 +17,7 @@ titles = {
     "\u2199\ufe0f": "Read generation parameters from prompt or last generation if prompt is empty into user interface.",
     "\u{1f4c2}": "Open images output directory",
     "\u{1f4be}": "Save style",
-    "\U0001F5D1": "Clear prompt",
+    "\u{1f5d1}": "Clear prompt",
     "\u{1f4cb}": "Apply selected styles to current prompt",
     "\u{1f4d2}": "Paste available values into the field",
     "\u{1f3b4}": "Show extra networks",
@@ -66,8 +66,8 @@ titles = {
 
     "Interrogate": "Reconstruct prompt from existing image and put it into the prompt field.",
 
-    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
+    "Images filename pattern": "Use following tags to define how filenames for images are chosen: [steps], [cfg], [prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
-    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
+    "Directory name pattern": "Use following tags to define how subdirectories for images and grids are chosen: [steps], [cfg],[prompt_hash], [prompt], [prompt_no_styles], [prompt_spaces], [width], [height], [styles], [sampler], [seed], [model_hash], [model_name], [prompt_words], [date], [datetime], [datetime<Format>], [datetime<Format><Time Zone>], [job_timestamp]; leave empty for default.",
     "Max prompt words": "Set the maximum number of words to be used in the [prompt_words] option; ATTENTION: If the words are too long, they may exceed the maximum length of the file path that the system can handle",
 
     "Loopback": "Process an image, use it as an input, repeat.",

javascript/ui.js

@@ -191,6 +191,28 @@ function confirm_clear_prompt(prompt, negative_prompt) {
     return [prompt, negative_prompt]
 }
 
+
+promptTokecountUpdateFuncs = {}
+
+function recalculatePromptTokens(name){
+    if(promptTokecountUpdateFuncs[name]){
+        promptTokecountUpdateFuncs[name]()
+    }
+}
+
+function recalculate_prompts_txt2img(){
+    recalculatePromptTokens('txt2img_prompt')
+    recalculatePromptTokens('txt2img_neg_prompt')
+    return args_to_array(arguments);
+}
+
+function recalculate_prompts_img2img(){
+    recalculatePromptTokens('img2img_prompt')
+    recalculatePromptTokens('img2img_neg_prompt')
+    return args_to_array(arguments);
+}
+
+
 opts = {}
 onUiUpdate(function(){
 	if(Object.keys(opts).length != 0) return;
@@ -232,14 +254,12 @@ onUiUpdate(function(){
             return
         }
 
-
         prompt.parentElement.insertBefore(counter, prompt)
         counter.classList.add("token-counter")
         prompt.parentElement.style.position = "relative"
 
-		textarea.addEventListener("input", function(){
+		promptTokecountUpdateFuncs[id] = function(){ update_token_counter(id_button); }
-		    update_token_counter(id_button);
+		textarea.addEventListener("input", promptTokecountUpdateFuncs[id]);
-		});
     }
 
     registerTextarea('txt2img_prompt', 'txt2img_token_counter', 'txt2img_token_button')
@@ -273,7 +293,7 @@ onOptionsChanged(function(){
 
 let txt2img_textarea, img2img_textarea = undefined;
 let wait_time = 800
-let token_timeout;
+let token_timeouts = {};
 
 function update_txt2img_tokens(...args) {
 	update_token_counter("txt2img_token_button")
@@ -290,9 +310,9 @@ function update_img2img_tokens(...args) {
 }
 
 function update_token_counter(button_id) {
-	if (token_timeout)
+	if (token_timeouts[button_id])
-		clearTimeout(token_timeout);
+		clearTimeout(token_timeouts[button_id]);
-	token_timeout = setTimeout(() => gradioApp().getElementById(button_id)?.click(), wait_time);
+	token_timeouts[button_id] = setTimeout(() => gradioApp().getElementById(button_id)?.click(), wait_time);
 }
 
 function restart_reload(){

launch.py

@@ -223,6 +223,7 @@ def prepare_environment():
     requirements_file = os.environ.get('REQS_FILE', "requirements_versions.txt")
     commandline_args = os.environ.get('COMMANDLINE_ARGS', "")
 
+    xformers_package = os.environ.get('XFORMERS_PACKAGE', 'xformers==0.0.16rc425')
     gfpgan_package = os.environ.get('GFPGAN_PACKAGE', "git+https://github.com/TencentARC/GFPGAN.git@8d2447a2d918f8eba5a4a01463fd48e45126a379")
     clip_package = os.environ.get('CLIP_PACKAGE', "git+https://github.com/openai/CLIP.git@d50d76daa670286dd6cacf3bcd80b5e4823fc8e1")
     openclip_package = os.environ.get('OPENCLIP_PACKAGE', "git+https://github.com/mlfoundations/open_clip.git@bb6e834e9c70d9c27d0dc3ecedeebeaeb1ffad6b")
@@ -282,14 +283,14 @@ def prepare_environment():
     if (not is_installed("xformers") or reinstall_xformers) and xformers:
         if platform.system() == "Windows":
             if platform.python_version().startswith("3.10"):
-                run_pip(f"install -U -I --no-deps xformers==0.0.16rc425", "xformers")
+                run_pip(f"install -U -I --no-deps {xformers_package}", "xformers")
             else:
                 print("Installation of xformers is not supported in this version of Python.")
                 print("You can also check this and build manually: https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Xformers#building-xformers-on-windows-by-duckness")
                 if not is_installed("xformers"):
                     exit(0)
         elif platform.system() == "Linux":
-            run_pip("install xformers==0.0.16rc425", "xformers")
+            run_pip(f"install {xformers_package}", "xformers")
 
     if not is_installed("pyngrok") and ngrok:
         run_pip("install pyngrok", "ngrok")

modules/devices.py

@@ -1,21 +1,17 @@
-import sys, os, shlex
+import sys
 import contextlib
 import torch
 from modules import errors
-from packaging import version
+
+if sys.platform == "darwin":
+    from modules import mac_specific
 
 
-# has_mps is only available in nightly pytorch (for now) and macOS 12.3+.
-# check `getattr` and try it for compatibility
 def has_mps() -> bool:
-    if not getattr(torch, 'has_mps', False):
+    if sys.platform != "darwin":
         return False
-    try:
+    else:
-        torch.zeros(1).to(torch.device("mps"))
+        return mac_specific.has_mps
-        return True
-    except Exception:
-        return False
-
 
 def extract_device_id(args, name):
     for x in range(len(args)):
@@ -154,56 +150,3 @@ def test_for_nans(x, where):
     message += " Use --disable-nan-check commandline argument to disable this check."
 
     raise NansException(message)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/79383
-orig_tensor_to = torch.Tensor.to
-def tensor_to_fix(self, *args, **kwargs):
-    if self.device.type != 'mps' and \
-       ((len(args) > 0 and isinstance(args[0], torch.device) and args[0].type == 'mps') or \
-       (isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps')):
-        self = self.contiguous()
-    return orig_tensor_to(self, *args, **kwargs)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/80800 
-orig_layer_norm = torch.nn.functional.layer_norm
-def layer_norm_fix(*args, **kwargs):
-    if len(args) > 0 and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps':
-        args = list(args)
-        args[0] = args[0].contiguous()
-    return orig_layer_norm(*args, **kwargs)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/90532
-orig_tensor_numpy = torch.Tensor.numpy
-def numpy_fix(self, *args, **kwargs):
-    if self.requires_grad:
-        self = self.detach()
-    return orig_tensor_numpy(self, *args, **kwargs)
-
-
-# MPS workaround for https://github.com/pytorch/pytorch/issues/89784
-orig_cumsum = torch.cumsum
-orig_Tensor_cumsum = torch.Tensor.cumsum
-def cumsum_fix(input, cumsum_func, *args, **kwargs):
-    if input.device.type == 'mps':
-        output_dtype = kwargs.get('dtype', input.dtype)
-        if output_dtype == torch.int64:
-            return cumsum_func(input.cpu(), *args, **kwargs).to(input.device)
-        elif cumsum_needs_bool_fix and output_dtype == torch.bool or cumsum_needs_int_fix and (output_dtype == torch.int8 or output_dtype == torch.int16):
-            return cumsum_func(input.to(torch.int32), *args, **kwargs).to(torch.int64)
-    return cumsum_func(input, *args, **kwargs)
-
-
-if has_mps():
-    if version.parse(torch.__version__) < version.parse("1.13"):
-        # PyTorch 1.13 doesn't need these fixes but unfortunately is slower and has regressions that prevent training from working
-        torch.Tensor.to = tensor_to_fix
-        torch.nn.functional.layer_norm = layer_norm_fix
-        torch.Tensor.numpy = numpy_fix
-    elif version.parse(torch.__version__) > version.parse("1.13.1"):
-        cumsum_needs_int_fix = not torch.Tensor([1,2]).to(torch.device("mps")).equal(torch.ShortTensor([1,1]).to(torch.device("mps")).cumsum(0))
-        cumsum_needs_bool_fix = not torch.BoolTensor([True,True]).to(device=torch.device("mps"), dtype=torch.int64).equal(torch.BoolTensor([True,False]).to(torch.device("mps")).cumsum(0))
-        torch.cumsum = lambda input, *args, **kwargs: ( cumsum_fix(input, orig_cumsum, *args, **kwargs) )
-        torch.Tensor.cumsum = lambda self, *args, **kwargs: ( cumsum_fix(self, orig_Tensor_cumsum, *args, **kwargs) )

modules/generation_parameters_copypaste.py

@@ -1,4 +1,5 @@
 import base64
+import html
 import io
 import math
 import os
@@ -16,13 +17,23 @@ re_param = re.compile(re_param_code)
 re_imagesize = re.compile(r"^(\d+)x(\d+)$")
 re_hypernet_hash = re.compile("\(([0-9a-f]+)\)$")
 type_of_gr_update = type(gr.update())
+
 paste_fields = {}
-bind_list = []
+registered_param_bindings = []
+
+
+class ParamBinding:
+    def __init__(self, paste_button, tabname, source_text_component=None, source_image_component=None, source_tabname=None, override_settings_component=None):
+        self.paste_button = paste_button
+        self.tabname = tabname
+        self.source_text_component = source_text_component
+        self.source_image_component = source_image_component
+        self.source_tabname = source_tabname
+        self.override_settings_component = override_settings_component
 
 
 def reset():
     paste_fields.clear()
-    bind_list.clear()
 
 
 def quote(text):
@@ -74,26 +85,6 @@ def add_paste_fields(tabname, init_img, fields):
         modules.ui.img2img_paste_fields = fields
 
 
-def integrate_settings_paste_fields(component_dict):
-    from modules import ui
-
-    settings_map = {
-        'CLIP_stop_at_last_layers': 'Clip skip',
-        'inpainting_mask_weight': 'Conditional mask weight',
-        'sd_model_checkpoint': 'Model hash',
-        'eta_noise_seed_delta': 'ENSD',
-        'initial_noise_multiplier': 'Noise multiplier',
-    }
-    settings_paste_fields = [
-        (component_dict[k], lambda d, k=k, v=v: ui.apply_setting(k, d.get(v, None)))
-        for k, v in settings_map.items()
-    ]
-
-    for tabname, info in paste_fields.items():
-        if info["fields"] is not None:
-            info["fields"] += settings_paste_fields
-
-
 def create_buttons(tabs_list):
     buttons = {}
     for tab in tabs_list:
@@ -101,9 +92,60 @@ def create_buttons(tabs_list):
     return buttons
 
 
-#if send_generate_info is a tab name, mean generate_info comes from the params fields of the tab
 def bind_buttons(buttons, send_image, send_generate_info):
-    bind_list.append([buttons, send_image, send_generate_info])
+    """old function for backwards compatibility; do not use this, use register_paste_params_button"""
+    for tabname, button in buttons.items():
+        source_text_component = send_generate_info if isinstance(send_generate_info, gr.components.Component) else None
+        source_tabname = send_generate_info if isinstance(send_generate_info, str) else None
+
+        register_paste_params_button(ParamBinding(paste_button=button, tabname=tabname, source_text_component=source_text_component, source_image_component=send_image, source_tabname=source_tabname))
+
+
+def register_paste_params_button(binding: ParamBinding):
+    registered_param_bindings.append(binding)
+
+
+def connect_paste_params_buttons():
+    binding: ParamBinding
+    for binding in registered_param_bindings:
+        destination_image_component = paste_fields[binding.tabname]["init_img"]
+        fields = paste_fields[binding.tabname]["fields"]
+
+        destination_width_component = next(iter([field for field, name in fields if name == "Size-1"] if fields else []), None)
+        destination_height_component = next(iter([field for field, name in fields if name == "Size-2"] if fields else []), None)
+
+        if binding.source_image_component and destination_image_component:
+            if isinstance(binding.source_image_component, gr.Gallery):
+                func = send_image_and_dimensions if destination_width_component else image_from_url_text
+                jsfunc = "extract_image_from_gallery"
+            else:
+                func = send_image_and_dimensions if destination_width_component else lambda x: x
+                jsfunc = None
+
+            binding.paste_button.click(
+                fn=func,
+                _js=jsfunc,
+                inputs=[binding.source_image_component],
+                outputs=[destination_image_component, destination_width_component, destination_height_component] if destination_width_component else [destination_image_component],
+            )
+
+        if binding.source_text_component is not None and fields is not None:
+            connect_paste(binding.paste_button, fields, binding.source_text_component, binding.override_settings_component, binding.tabname)
+
+        if binding.source_tabname is not None and fields is not None:
+            paste_field_names = ['Prompt', 'Negative prompt', 'Steps', 'Face restoration'] + (["Seed"] if shared.opts.send_seed else [])
+            binding.paste_button.click(
+                fn=lambda *x: x,
+                inputs=[field for field, name in paste_fields[binding.source_tabname]["fields"] if name in paste_field_names],
+                outputs=[field for field, name in fields if name in paste_field_names],
+            )
+
+        binding.paste_button.click(
+            fn=None,
+            _js=f"switch_to_{binding.tabname}",
+            inputs=None,
+            outputs=None,
+        )
 
 
 def send_image_and_dimensions(x):
@@ -122,49 +164,6 @@ def send_image_and_dimensions(x):
     return img, w, h
 
 
-def run_bind():
-    for buttons, source_image_component, send_generate_info in bind_list:
-        for tab in buttons:
-            button = buttons[tab]
-            destination_image_component = paste_fields[tab]["init_img"]
-            fields = paste_fields[tab]["fields"]
-
-            destination_width_component = next(iter([field for field, name in fields if name == "Size-1"] if fields else []), None)
-            destination_height_component = next(iter([field for field, name in fields if name == "Size-2"] if fields else []), None)
-
-            if source_image_component and destination_image_component:
-                if isinstance(source_image_component, gr.Gallery):
-                    func = send_image_and_dimensions if destination_width_component else image_from_url_text
-                    jsfunc = "extract_image_from_gallery"
-                else:
-                    func = send_image_and_dimensions if destination_width_component else lambda x: x
-                    jsfunc = None
-
-                button.click(
-                    fn=func,
-                    _js=jsfunc,
-                    inputs=[source_image_component],
-                    outputs=[destination_image_component, destination_width_component, destination_height_component] if destination_width_component else [destination_image_component],
-                )
-
-            if send_generate_info and fields is not None:
-                if send_generate_info in paste_fields:
-                    paste_field_names = ['Prompt', 'Negative prompt', 'Steps', 'Face restoration'] + (["Seed"] if shared.opts.send_seed else [])
-                    button.click(
-                        fn=lambda *x: x,
-                        inputs=[field for field, name in paste_fields[send_generate_info]["fields"] if name in paste_field_names],
-                        outputs=[field for field, name in fields if name in paste_field_names],
-                    )
-                else:
-                    connect_paste(button, fields, send_generate_info)
-
-            button.click(
-                fn=None,
-                _js=f"switch_to_{tab}",
-                inputs=None,
-                outputs=None,
-            )
-
 
 def find_hypernetwork_key(hypernet_name, hypernet_hash=None):
     """Determines the config parameter name to use for the hypernet based on the parameters in the infotext.
@@ -286,7 +285,50 @@ Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 965400086, Size: 512x512, Model
     return res
 
 
-def connect_paste(button, paste_fields, input_comp, jsfunc=None):
+settings_map = {}
+
+infotext_to_setting_name_mapping = [
+    ('Clip skip', 'CLIP_stop_at_last_layers', ),
+    ('Conditional mask weight', 'inpainting_mask_weight'),
+    ('Model hash', 'sd_model_checkpoint'),
+    ('ENSD', 'eta_noise_seed_delta'),
+    ('Noise multiplier', 'initial_noise_multiplier'),
+    ('Eta', 'eta_ancestral'),
+    ('Eta DDIM', 'eta_ddim'),
+    ('Discard penultimate sigma', 'always_discard_next_to_last_sigma')
+]
+
+
+def create_override_settings_dict(text_pairs):
+    """creates processing's override_settings parameters from gradio's multiselect
+
+    Example input:
+        ['Clip skip: 2', 'Model hash: e6e99610c4', 'ENSD: 31337']
+
+    Example output:
+        {'CLIP_stop_at_last_layers': 2, 'sd_model_checkpoint': 'e6e99610c4', 'eta_noise_seed_delta': 31337}
+    """
+
+    res = {}
+
+    params = {}
+    for pair in text_pairs:
+        k, v = pair.split(":", maxsplit=1)
+
+        params[k] = v.strip()
+
+    for param_name, setting_name in infotext_to_setting_name_mapping:
+        value = params.get(param_name, None)
+
+        if value is None:
+            continue
+
+        res[setting_name] = shared.opts.cast_value(setting_name, value)
+
+    return res
+
+
+def connect_paste(button, paste_fields, input_comp, override_settings_component, tabname):
     def paste_func(prompt):
         if not prompt and not shared.cmd_opts.hide_ui_dir_config:
             filename = os.path.join(data_path, "params.txt")
@@ -323,9 +365,35 @@ def connect_paste(button, paste_fields, input_comp, jsfunc=None):
 
         return res
 
+    if override_settings_component is not None:
+        def paste_settings(params):
+            vals = {}
+
+            for param_name, setting_name in infotext_to_setting_name_mapping:
+                v = params.get(param_name, None)
+                if v is None:
+                    continue
+
+                if setting_name == "sd_model_checkpoint" and shared.opts.disable_weights_auto_swap:
+                    continue
+
+                v = shared.opts.cast_value(setting_name, v)
+                current_value = getattr(shared.opts, setting_name, None)
+
+                if v == current_value:
+                    continue
+
+                vals[param_name] = v
+
+            vals_pairs = [f"{k}: {v}" for k, v in vals.items()]
+
+            return gr.Dropdown.update(value=vals_pairs, choices=vals_pairs, visible=len(vals_pairs) > 0)
+
+        paste_fields = paste_fields + [(override_settings_component, paste_settings)]
+
     button.click(
         fn=paste_func,
-        _js=jsfunc,
+        _js=f"recalculate_prompts_{tabname}",
         inputs=[input_comp],
         outputs=[x[0] for x in paste_fields],
     )

modules/hashes.py

@@ -4,6 +4,7 @@ import os.path
 
 import filelock
 
+from modules import shared
 from modules.paths import data_path
 
 
@@ -68,6 +69,9 @@ def sha256(filename, title):
     if sha256_value is not None:
         return sha256_value
 
+    if shared.cmd_opts.no_hashing:
+        return None
+
     print(f"Calculating sha256 for {filename}: ", end='')
     sha256_value = calculate_sha256(filename)
     print(f"{sha256_value}")

modules/hypernetworks/hypernetwork.py

@@ -307,7 +307,7 @@ class Hypernetwork:
     def shorthash(self):
         sha256 = hashes.sha256(self.filename, f'hypernet/{self.name}')
 
-        return sha256[0:10]
+        return sha256[0:10] if sha256 else None
 
 
 def list_hypernetworks(path):

modules/images.py

@@ -16,6 +16,7 @@ from PIL import Image, ImageFont, ImageDraw, PngImagePlugin
 from fonts.ttf import Roboto
 import string
 import json
+import hashlib
 
 from modules import sd_samplers, shared, script_callbacks
 from modules.shared import opts, cmd_opts
@@ -130,7 +131,7 @@ class GridAnnotation:
         self.size = None
 
 
-def draw_grid_annotations(im, width, height, hor_texts, ver_texts):
+def draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin=0):
     def wrap(drawing, text, font, line_length):
         lines = ['']
         for word in text.split():
@@ -194,32 +195,35 @@ def draw_grid_annotations(im, width, height, hor_texts, ver_texts):
             line.allowed_width = allowed_width
 
     hor_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing for lines in hor_texts]
-    ver_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing * len(lines) for lines in
+    ver_text_heights = [sum([line.size[1] + line_spacing for line in lines]) - line_spacing * len(lines) for lines in ver_texts]
-                        ver_texts]
 
     pad_top = 0 if sum(hor_text_heights) == 0 else max(hor_text_heights) + line_spacing * 2
 
-    result = Image.new("RGB", (im.width + pad_left, im.height + pad_top), "white")
+    result = Image.new("RGB", (im.width + pad_left + margin * (cols-1), im.height + pad_top + margin * (rows-1)), "white")
-    result.paste(im, (pad_left, pad_top))
+
+    for row in range(rows):
+        for col in range(cols):
+            cell = im.crop((width * col, height * row, width * (col+1), height * (row+1)))
+            result.paste(cell, (pad_left + (width + margin) * col, pad_top + (height + margin) * row))
 
     d = ImageDraw.Draw(result)
 
     for col in range(cols):
-        x = pad_left + width * col + width / 2
+        x = pad_left + (width + margin) * col + width / 2
         y = pad_top / 2 - hor_text_heights[col] / 2
 
         draw_texts(d, x, y, hor_texts[col], fnt, fontsize)
 
     for row in range(rows):
         x = pad_left / 2
-        y = pad_top + height * row + height / 2 - ver_text_heights[row] / 2
+        y = pad_top + (height + margin) * row + height / 2 - ver_text_heights[row] / 2
 
         draw_texts(d, x, y, ver_texts[row], fnt, fontsize)
 
     return result
 
 
-def draw_prompt_matrix(im, width, height, all_prompts):
+def draw_prompt_matrix(im, width, height, all_prompts, margin=0):
     prompts = all_prompts[1:]
     boundary = math.ceil(len(prompts) / 2)
 
@@ -229,7 +233,7 @@ def draw_prompt_matrix(im, width, height, all_prompts):
     hor_texts = [[GridAnnotation(x, is_active=pos & (1 << i) != 0) for i, x in enumerate(prompts_horiz)] for pos in range(1 << len(prompts_horiz))]
     ver_texts = [[GridAnnotation(x, is_active=pos & (1 << i) != 0) for i, x in enumerate(prompts_vert)] for pos in range(1 << len(prompts_vert))]
 
-    return draw_grid_annotations(im, width, height, hor_texts, ver_texts)
+    return draw_grid_annotations(im, width, height, hor_texts, ver_texts, margin)
 
 
 def resize_image(resize_mode, im, width, height, upscaler_name=None):
@@ -340,6 +344,7 @@ class FilenameGenerator:
         'date': lambda self: datetime.datetime.now().strftime('%Y-%m-%d'),
         'datetime': lambda self, *args: self.datetime(*args),  # accepts formats: [datetime], [datetime<Format>], [datetime<Format><Time Zone>]
         'job_timestamp': lambda self: getattr(self.p, "job_timestamp", shared.state.job_timestamp),
+        'prompt_hash': lambda self: hashlib.sha256(self.prompt.encode()).hexdigest()[0:8],
         'prompt': lambda self: sanitize_filename_part(self.prompt),
         'prompt_no_styles': lambda self: self.prompt_no_style(),
         'prompt_spaces': lambda self: sanitize_filename_part(self.prompt, replace_spaces=False),

modules/img2img.py

@@ -7,6 +7,7 @@ import numpy as np
 from PIL import Image, ImageOps, ImageFilter, ImageEnhance, ImageChops
 
 from modules import devices, sd_samplers
+from modules.generation_parameters_copypaste import create_override_settings_dict
 from modules.processing import Processed, StableDiffusionProcessingImg2Img, process_images
 from modules.shared import opts, state
 import modules.shared as shared
@@ -75,7 +76,9 @@ def process_batch(p, input_dir, output_dir, inpaint_mask_dir, args):
                 processed_image.save(os.path.join(output_dir, filename))
 
 
-def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, *args):
+def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_styles, init_img, sketch, init_img_with_mask, inpaint_color_sketch, inpaint_color_sketch_orig, init_img_inpaint, init_mask_inpaint, steps: int, sampler_index: int, mask_blur: int, mask_alpha: float, inpainting_fill: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, image_cfg_scale: float, denoising_strength: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, resize_mode: int, inpaint_full_res: bool, inpaint_full_res_padding: int, inpainting_mask_invert: int, img2img_batch_input_dir: str, img2img_batch_output_dir: str, img2img_batch_inpaint_mask_dir: str, override_settings_texts, *args):
+    override_settings = create_override_settings_dict(override_settings_texts)
+
     is_batch = mode == 5
 
     if mode == 0:  # img2img
@@ -139,9 +142,11 @@ def img2img(id_task: str, mode: int, prompt: str, negative_prompt: str, prompt_s
         inpainting_fill=inpainting_fill,
         resize_mode=resize_mode,
         denoising_strength=denoising_strength,
+        image_cfg_scale=image_cfg_scale,
         inpaint_full_res=inpaint_full_res,
         inpaint_full_res_padding=inpaint_full_res_padding,
         inpainting_mask_invert=inpainting_mask_invert,
+        override_settings=override_settings,
     )
 
     p.scripts = modules.scripts.scripts_txt2img

modules/mac_specific.py

@@ -0,0 +1,53 @@
+import torch
+from modules import paths
+from modules.sd_hijack_utils import CondFunc
+from packaging import version
+
+
+# has_mps is only available in nightly pytorch (for now) and macOS 12.3+.
+# check `getattr` and try it for compatibility
+def check_for_mps() -> bool:
+    if not getattr(torch, 'has_mps', False):
+        return False
+    try:
+        torch.zeros(1).to(torch.device("mps"))
+        return True
+    except Exception:
+        return False
+has_mps = check_for_mps()
+
+
+# MPS workaround for https://github.com/pytorch/pytorch/issues/89784
+def cumsum_fix(input, cumsum_func, *args, **kwargs):
+    if input.device.type == 'mps':
+        output_dtype = kwargs.get('dtype', input.dtype)
+        if output_dtype == torch.int64:
+            return cumsum_func(input.cpu(), *args, **kwargs).to(input.device)
+        elif cumsum_needs_bool_fix and output_dtype == torch.bool or cumsum_needs_int_fix and (output_dtype == torch.int8 or output_dtype == torch.int16):
+            return cumsum_func(input.to(torch.int32), *args, **kwargs).to(torch.int64)
+    return cumsum_func(input, *args, **kwargs)
+
+
+if has_mps:
+    # MPS fix for randn in torchsde
+    CondFunc('torchsde._brownian.brownian_interval._randn', lambda _, size, dtype, device, seed: torch.randn(size, dtype=dtype, device=torch.device("cpu"), generator=torch.Generator(torch.device("cpu")).manual_seed(int(seed))).to(device), lambda _, size, dtype, device, seed: device.type == 'mps')
+
+    if version.parse(torch.__version__) < version.parse("1.13"):
+        # PyTorch 1.13 doesn't need these fixes but unfortunately is slower and has regressions that prevent training from working
+
+        # MPS workaround for https://github.com/pytorch/pytorch/issues/79383
+        CondFunc('torch.Tensor.to', lambda orig_func, self, *args, **kwargs: orig_func(self.contiguous(), *args, **kwargs),
+                                                          lambda _, self, *args, **kwargs: self.device.type != 'mps' and (args and isinstance(args[0], torch.device) and args[0].type == 'mps' or isinstance(kwargs.get('device'), torch.device) and kwargs['device'].type == 'mps'))
+        # MPS workaround for https://github.com/pytorch/pytorch/issues/80800 
+        CondFunc('torch.nn.functional.layer_norm', lambda orig_func, *args, **kwargs: orig_func(*([args[0].contiguous()] + list(args[1:])), **kwargs),
+                                                                                        lambda _, *args, **kwargs: args and isinstance(args[0], torch.Tensor) and args[0].device.type == 'mps')
+        # MPS workaround for https://github.com/pytorch/pytorch/issues/90532
+        CondFunc('torch.Tensor.numpy', lambda orig_func, self, *args, **kwargs: orig_func(self.detach(), *args, **kwargs), lambda _, self, *args, **kwargs: self.requires_grad)
+    elif version.parse(torch.__version__) > version.parse("1.13.1"):
+        cumsum_needs_int_fix = not torch.Tensor([1,2]).to(torch.device("mps")).equal(torch.ShortTensor([1,1]).to(torch.device("mps")).cumsum(0))
+        cumsum_needs_bool_fix = not torch.BoolTensor([True,True]).to(device=torch.device("mps"), dtype=torch.int64).equal(torch.BoolTensor([True,False]).to(torch.device("mps")).cumsum(0))
+        cumsum_fix_func = lambda orig_func, input, *args, **kwargs: cumsum_fix(input, orig_func, *args, **kwargs)
+        CondFunc('torch.cumsum', cumsum_fix_func, None)
+        CondFunc('torch.Tensor.cumsum', cumsum_fix_func, None)
+        CondFunc('torch.narrow', lambda orig_func, *args, **kwargs: orig_func(*args, **kwargs).clone(), None)
+

modules/modelloader.py

@@ -45,6 +45,9 @@ def load_models(model_path: str, model_url: str = None, command_path: str = None
                     full_path = file
                     if os.path.isdir(full_path):
                         continue
+                    if os.path.islink(full_path) and not os.path.exists(full_path):
+                        print(f"Skipping broken symlink: {full_path}")
+                        continue
                     if ext_blacklist is not None and any([full_path.endswith(x) for x in ext_blacklist]):
                         continue
                     if len(ext_filter) != 0:

modules/processing.py

@@ -186,7 +186,7 @@ class StableDiffusionProcessing:
         return conditioning
 
     def edit_image_conditioning(self, source_image):
-        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))
+        conditioning_image = self.sd_model.encode_first_stage(source_image).mode()
 
         return conditioning_image
 
@@ -268,6 +268,7 @@ class Processed:
         self.height = p.height
         self.sampler_name = p.sampler_name
         self.cfg_scale = p.cfg_scale
+        self.image_cfg_scale = getattr(p, 'image_cfg_scale', None)
         self.steps = p.steps
         self.batch_size = p.batch_size
         self.restore_faces = p.restore_faces
@@ -445,6 +446,7 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
         "Steps": p.steps,
         "Sampler": p.sampler_name,
         "CFG scale": p.cfg_scale,
+        "Image CFG scale": getattr(p, 'image_cfg_scale', None),
         "Seed": all_seeds[index],
         "Face restoration": (opts.face_restoration_model if p.restore_faces else None),
         "Size": f"{p.width}x{p.height}",
@@ -455,7 +457,6 @@ def create_infotext(p, all_prompts, all_seeds, all_subseeds, comments=None, iter
         "Seed resize from": (None if p.seed_resize_from_w == 0 or p.seed_resize_from_h == 0 else f"{p.seed_resize_from_w}x{p.seed_resize_from_h}"),
         "Denoising strength": getattr(p, 'denoising_strength', None),
         "Conditional mask weight": getattr(p, "inpainting_mask_weight", shared.opts.inpainting_mask_weight) if p.is_using_inpainting_conditioning else None,
-        "Eta": (None if p.sampler is None or p.sampler.eta == p.sampler.default_eta else p.sampler.eta),
         "Clip skip": None if clip_skip <= 1 else clip_skip,
         "ENSD": None if opts.eta_noise_seed_delta == 0 else opts.eta_noise_seed_delta,
     }
@@ -902,12 +903,13 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
 class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
     sampler = None
 
-    def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.75, mask: Any = None, mask_blur: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, **kwargs):
+    def __init__(self, init_images: list = None, resize_mode: int = 0, denoising_strength: float = 0.75, image_cfg_scale: float = None, mask: Any = None, mask_blur: int = 4, inpainting_fill: int = 0, inpaint_full_res: bool = True, inpaint_full_res_padding: int = 0, inpainting_mask_invert: int = 0, initial_noise_multiplier: float = None, **kwargs):
         super().__init__(**kwargs)
 
         self.init_images = init_images
         self.resize_mode: int = resize_mode
         self.denoising_strength: float = denoising_strength
+        self.image_cfg_scale: float = image_cfg_scale if shared.sd_model.cond_stage_key == "edit" else None
         self.init_latent = None
         self.image_mask = mask
         self.latent_mask = None

modules/sd_disable_initialization.py

@@ -20,8 +20,9 @@ class DisableInitialization:
     ```
     """
 
-    def __init__(self):
+    def __init__(self, disable_clip=True):
         self.replaced = []
+        self.disable_clip = disable_clip
 
     def replace(self, obj, field, func):
         original = getattr(obj, field, None)
@@ -75,12 +76,14 @@ class DisableInitialization:
         self.replace(torch.nn.init, 'kaiming_uniform_', do_nothing)
         self.replace(torch.nn.init, '_no_grad_normal_', do_nothing)
         self.replace(torch.nn.init, '_no_grad_uniform_', do_nothing)
-        self.create_model_and_transforms = self.replace(open_clip, 'create_model_and_transforms', create_model_and_transforms_without_pretrained)
+
-        self.CLIPTextModel_from_pretrained = self.replace(ldm.modules.encoders.modules.CLIPTextModel, 'from_pretrained', CLIPTextModel_from_pretrained)
+        if self.disable_clip:
-        self.transformers_modeling_utils_load_pretrained_model = self.replace(transformers.modeling_utils.PreTrainedModel, '_load_pretrained_model', transformers_modeling_utils_load_pretrained_model)
+            self.create_model_and_transforms = self.replace(open_clip, 'create_model_and_transforms', create_model_and_transforms_without_pretrained)
-        self.transformers_tokenization_utils_base_cached_file = self.replace(transformers.tokenization_utils_base, 'cached_file', transformers_tokenization_utils_base_cached_file)
+            self.CLIPTextModel_from_pretrained = self.replace(ldm.modules.encoders.modules.CLIPTextModel, 'from_pretrained', CLIPTextModel_from_pretrained)
-        self.transformers_configuration_utils_cached_file = self.replace(transformers.configuration_utils, 'cached_file', transformers_configuration_utils_cached_file)
+            self.transformers_modeling_utils_load_pretrained_model = self.replace(transformers.modeling_utils.PreTrainedModel, '_load_pretrained_model', transformers_modeling_utils_load_pretrained_model)
-        self.transformers_utils_hub_get_from_cache = self.replace(transformers.utils.hub, 'get_from_cache', transformers_utils_hub_get_from_cache)
+            self.transformers_tokenization_utils_base_cached_file = self.replace(transformers.tokenization_utils_base, 'cached_file', transformers_tokenization_utils_base_cached_file)
+            self.transformers_configuration_utils_cached_file = self.replace(transformers.configuration_utils, 'cached_file', transformers_configuration_utils_cached_file)
+            self.transformers_utils_hub_get_from_cache = self.replace(transformers.utils.hub, 'get_from_cache', transformers_utils_hub_get_from_cache)
 
     def __exit__(self, exc_type, exc_val, exc_tb):
         for obj, field, original in self.replaced:

modules/sd_models.py

@@ -59,13 +59,17 @@ class CheckpointInfo:
 
     def calculate_shorthash(self):
         self.sha256 = hashes.sha256(self.filename, "checkpoint/" + self.name)
+        if self.sha256 is None:
+            return
+
         self.shorthash = self.sha256[0:10]
 
         if self.shorthash not in self.ids:
-            self.ids += [self.shorthash, self.sha256]
+            self.ids += [self.shorthash, self.sha256, f'{self.name} [{self.shorthash}]']
-            self.register()
 
+        checkpoints_list.pop(self.title)
         self.title = f'{self.name} [{self.shorthash}]'
+        self.register()
 
         return self.shorthash
 
@@ -158,7 +162,7 @@ def select_checkpoint():
         print(f" - directory {model_path}", file=sys.stderr)
         if shared.cmd_opts.ckpt_dir is not None:
             print(f" - directory {os.path.abspath(shared.cmd_opts.ckpt_dir)}", file=sys.stderr)
-        print("Can't run without a checkpoint. Find and place a .ckpt file into any of those locations. The program will exit.", file=sys.stderr)
+        print("Can't run without a checkpoint. Find and place a .ckpt or .safetensors file into any of those locations. The program will exit.", file=sys.stderr)
         exit(1)
 
     checkpoint_info = next(iter(checkpoints_list.values()))
@@ -350,6 +354,9 @@ def repair_config(sd_config):
         sd_config.model.params.unet_config.params.use_fp16 = True
 
 
+sd1_clip_weight = 'cond_stage_model.transformer.text_model.embeddings.token_embedding.weight'
+sd2_clip_weight = 'cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight'
+
 def load_model(checkpoint_info=None, already_loaded_state_dict=None, time_taken_to_load_state_dict=None):
     from modules import lowvram, sd_hijack
     checkpoint_info = checkpoint_info or select_checkpoint()
@@ -370,6 +377,7 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None, time_taken_
         state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
 
     checkpoint_config = sd_models_config.find_checkpoint_config(state_dict, checkpoint_info)
+    clip_is_included_into_sd = sd1_clip_weight in state_dict or sd2_clip_weight in state_dict
 
     timer.record("find config")
 
@@ -382,7 +390,7 @@ def load_model(checkpoint_info=None, already_loaded_state_dict=None, time_taken_
 
     sd_model = None
     try:
-        with sd_disable_initialization.DisableInitialization():
+        with sd_disable_initialization.DisableInitialization(disable_clip=clip_is_included_into_sd):
             sd_model = instantiate_from_config(sd_config.model)
     except Exception as e:
         pass

modules/sd_samplers.py

@@ -1,53 +1,11 @@
-from collections import namedtuple, deque
+from modules import sd_samplers_compvis, sd_samplers_kdiffusion, shared
-import numpy as np
-from math import floor
-import torch
-import tqdm
-from PIL import Image
-import inspect
-import k_diffusion.sampling
-import torchsde._brownian.brownian_interval
-import ldm.models.diffusion.ddim
-import ldm.models.diffusion.plms
-from modules import prompt_parser, devices, processing, images, sd_vae_approx
 
-from modules.shared import opts, cmd_opts, state
+# imports for functions that previously were here and are used by other modules
-import modules.shared as shared
+from modules.sd_samplers_common import samples_to_image_grid, sample_to_image
-from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback
-
-
-SamplerData = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options'])
-
-samplers_k_diffusion = [
-    ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {}),
-    ('Euler', 'sample_euler', ['k_euler'], {}),
-    ('LMS', 'sample_lms', ['k_lms'], {}),
-    ('Heun', 'sample_heun', ['k_heun'], {}),
-    ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True}),
-    ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True}),
-    ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}),
-    ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),
-    ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {}),
-    ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}),
-    ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}),
-    ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),
-    ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}),
-    ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}),
-    ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}),
-    ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}),
-    ('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras'}),
-]
-
-samplers_data_k_diffusion = [
-    SamplerData(label, lambda model, funcname=funcname: KDiffusionSampler(funcname, model), aliases, options)
-    for label, funcname, aliases, options in samplers_k_diffusion
-    if hasattr(k_diffusion.sampling, funcname)
-]
 
 all_samplers = [
-    *samplers_data_k_diffusion,
+    *sd_samplers_kdiffusion.samplers_data_k_diffusion,
-    SamplerData('DDIM', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {}),
+    *sd_samplers_compvis.samplers_data_compvis,
-    SamplerData('PLMS', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.plms.PLMSSampler, model), [], {}),
 ]
 all_samplers_map = {x.name: x for x in all_samplers}
 
@@ -73,8 +31,8 @@ def create_sampler(name, model):
 def set_samplers():
     global samplers, samplers_for_img2img
 
-    hidden = set(opts.hide_samplers)
+    hidden = set(shared.opts.hide_samplers)
-    hidden_img2img = set(opts.hide_samplers + ['PLMS'])
+    hidden_img2img = set(shared.opts.hide_samplers + ['PLMS'])
 
     samplers = [x for x in all_samplers if x.name not in hidden]
     samplers_for_img2img = [x for x in all_samplers if x.name not in hidden_img2img]
@@ -87,466 +45,3 @@ def set_samplers():
 
 
 set_samplers()
-
-sampler_extra_params = {
-    'sample_euler': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
-    'sample_heun': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
-    'sample_dpm_2': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
-}
-
-
-def setup_img2img_steps(p, steps=None):
-    if opts.img2img_fix_steps or steps is not None:
-        requested_steps = (steps or p.steps)
-        steps = int(requested_steps / min(p.denoising_strength, 0.999)) if p.denoising_strength > 0 else 0
-        t_enc = requested_steps - 1
-    else:
-        steps = p.steps
-        t_enc = int(min(p.denoising_strength, 0.999) * steps)
-
-    return steps, t_enc
-
-
-approximation_indexes = {"Full": 0, "Approx NN": 1, "Approx cheap": 2}
-
-
-def single_sample_to_image(sample, approximation=None):
-    if approximation is None:
-        approximation = approximation_indexes.get(opts.show_progress_type, 0)
-
-    if approximation == 2:
-        x_sample = sd_vae_approx.cheap_approximation(sample)
-    elif approximation == 1:
-        x_sample = sd_vae_approx.model()(sample.to(devices.device, devices.dtype).unsqueeze(0))[0].detach()
-    else:
-        x_sample = processing.decode_first_stage(shared.sd_model, sample.unsqueeze(0))[0]
-
-    x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0)
-    x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)
-    x_sample = x_sample.astype(np.uint8)
-    return Image.fromarray(x_sample)
-
-
-def sample_to_image(samples, index=0, approximation=None):
-    return single_sample_to_image(samples[index], approximation)
-
-
-def samples_to_image_grid(samples, approximation=None):
-    return images.image_grid([single_sample_to_image(sample, approximation) for sample in samples])
-
-
-def store_latent(decoded):
-    state.current_latent = decoded
-
-    if opts.live_previews_enable and opts.show_progress_every_n_steps > 0 and shared.state.sampling_step % opts.show_progress_every_n_steps == 0:
-        if not shared.parallel_processing_allowed:
-            shared.state.assign_current_image(sample_to_image(decoded))
-
-
-class InterruptedException(BaseException):
-    pass
-
-
-class VanillaStableDiffusionSampler:
-    def __init__(self, constructor, sd_model):
-        self.sampler = constructor(sd_model)
-        self.is_plms = hasattr(self.sampler, 'p_sample_plms')
-        self.orig_p_sample_ddim = self.sampler.p_sample_plms if self.is_plms else self.sampler.p_sample_ddim
-        self.mask = None
-        self.nmask = None
-        self.init_latent = None
-        self.sampler_noises = None
-        self.step = 0
-        self.stop_at = None
-        self.eta = None
-        self.default_eta = 0.0
-        self.config = None
-        self.last_latent = None
-
-        self.conditioning_key = sd_model.model.conditioning_key
-
-    def number_of_needed_noises(self, p):
-        return 0
-
-    def launch_sampling(self, steps, func):
-        state.sampling_steps = steps
-        state.sampling_step = 0
-
-        try:
-            return func()
-        except InterruptedException:
-            return self.last_latent
-
-    def p_sample_ddim_hook(self, x_dec, cond, ts, unconditional_conditioning, *args, **kwargs):
-        if state.interrupted or state.skipped:
-            raise InterruptedException
-
-        if self.stop_at is not None and self.step > self.stop_at:
-            raise InterruptedException
-
-        # Have to unwrap the inpainting conditioning here to perform pre-processing
-        image_conditioning = None
-        if isinstance(cond, dict):
-            image_conditioning = cond["c_concat"][0]
-            cond = cond["c_crossattn"][0]
-            unconditional_conditioning = unconditional_conditioning["c_crossattn"][0]
-
-        conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
-        unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step)
-
-        assert all([len(conds) == 1 for conds in conds_list]), 'composition via AND is not supported for DDIM/PLMS samplers'
-        cond = tensor
-
-        # for DDIM, shapes must match, we can't just process cond and uncond independently;
-        # filling unconditional_conditioning with repeats of the last vector to match length is
-        # not 100% correct but should work well enough
-        if unconditional_conditioning.shape[1] < cond.shape[1]:
-            last_vector = unconditional_conditioning[:, -1:]
-            last_vector_repeated = last_vector.repeat([1, cond.shape[1] - unconditional_conditioning.shape[1], 1])
-            unconditional_conditioning = torch.hstack([unconditional_conditioning, last_vector_repeated])
-        elif unconditional_conditioning.shape[1] > cond.shape[1]:
-            unconditional_conditioning = unconditional_conditioning[:, :cond.shape[1]]
-
-        if self.mask is not None:
-            img_orig = self.sampler.model.q_sample(self.init_latent, ts)
-            x_dec = img_orig * self.mask + self.nmask * x_dec
-
-        # Wrap the image conditioning back up since the DDIM code can accept the dict directly.
-        # Note that they need to be lists because it just concatenates them later.
-        if image_conditioning is not None:
-            cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]}
-            unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
-
-        res = self.orig_p_sample_ddim(x_dec, cond, ts, unconditional_conditioning=unconditional_conditioning, *args, **kwargs)
-
-        if self.mask is not None:
-            self.last_latent = self.init_latent * self.mask + self.nmask * res[1]
-        else:
-            self.last_latent = res[1]
-
-        store_latent(self.last_latent)
-
-        self.step += 1
-        state.sampling_step = self.step
-        shared.total_tqdm.update()
-
-        return res
-
-    def initialize(self, p):
-        self.eta = p.eta if p.eta is not None else opts.eta_ddim
-
-        for fieldname in ['p_sample_ddim', 'p_sample_plms']:
-            if hasattr(self.sampler, fieldname):
-                setattr(self.sampler, fieldname, self.p_sample_ddim_hook)
-
-        self.mask = p.mask if hasattr(p, 'mask') else None
-        self.nmask = p.nmask if hasattr(p, 'nmask') else None
-
-    def adjust_steps_if_invalid(self, p, num_steps):
-        if (self.config.name == 'DDIM' and p.ddim_discretize == 'uniform') or (self.config.name == 'PLMS'):
-            valid_step = 999 / (1000 // num_steps)
-            if valid_step == floor(valid_step):
-                return int(valid_step) + 1
-        
-        return num_steps
-
-    def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
-        steps, t_enc = setup_img2img_steps(p, steps)
-        steps = self.adjust_steps_if_invalid(p, steps)
-        self.initialize(p)
-
-        self.sampler.make_schedule(ddim_num_steps=steps, ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False)
-        x1 = self.sampler.stochastic_encode(x, torch.tensor([t_enc] * int(x.shape[0])).to(shared.device), noise=noise)
-
-        self.init_latent = x
-        self.last_latent = x
-        self.step = 0
-
-        # Wrap the conditioning models with additional image conditioning for inpainting model
-        if image_conditioning is not None:
-            conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
-            unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
-
-        samples = self.launch_sampling(t_enc + 1, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning))
-
-        return samples
-
-    def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
-        self.initialize(p)
-
-        self.init_latent = None
-        self.last_latent = x
-        self.step = 0
-
-        steps = self.adjust_steps_if_invalid(p, steps or p.steps)
-
-        # Wrap the conditioning models with additional image conditioning for inpainting model
-        # dummy_for_plms is needed because PLMS code checks the first item in the dict to have the right shape
-        if image_conditioning is not None:
-            conditioning = {"dummy_for_plms": np.zeros((conditioning.shape[0],)), "c_crossattn": [conditioning], "c_concat": [image_conditioning]}
-            unconditional_conditioning = {"c_crossattn": [unconditional_conditioning], "c_concat": [image_conditioning]}
-
-        samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
-
-        return samples_ddim
-
-
-class CFGDenoiser(torch.nn.Module):
-    def __init__(self, model):
-        super().__init__()
-        self.inner_model = model
-        self.mask = None
-        self.nmask = None
-        self.init_latent = None
-        self.step = 0
-
-    def combine_denoised(self, x_out, conds_list, uncond, cond_scale):
-        denoised_uncond = x_out[-uncond.shape[0]:]
-        denoised = torch.clone(denoised_uncond)
-
-        for i, conds in enumerate(conds_list):
-            for cond_index, weight in conds:
-                denoised[i] += (x_out[cond_index] - denoised_uncond[i]) * (weight * cond_scale)
-
-        return denoised
-
-    def forward(self, x, sigma, uncond, cond, cond_scale, image_cond):
-        if state.interrupted or state.skipped:
-            raise InterruptedException
-
-        conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
-        uncond = prompt_parser.reconstruct_cond_batch(uncond, self.step)
-
-        batch_size = len(conds_list)
-        repeats = [len(conds_list[i]) for i in range(batch_size)]
-
-        x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
-        image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
-        sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
-
-        denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)
-        cfg_denoiser_callback(denoiser_params)
-        x_in = denoiser_params.x
-        image_cond_in = denoiser_params.image_cond
-        sigma_in = denoiser_params.sigma
-
-        if tensor.shape[1] == uncond.shape[1]:
-            cond_in = torch.cat([tensor, uncond])
-
-            if shared.batch_cond_uncond:
-                x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
-            else:
-                x_out = torch.zeros_like(x_in)
-                for batch_offset in range(0, x_out.shape[0], batch_size):
-                    a = batch_offset
-                    b = a + batch_size
-                    x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [cond_in[a:b]], "c_concat": [image_cond_in[a:b]]})
-        else:
-            x_out = torch.zeros_like(x_in)
-            batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
-            for batch_offset in range(0, tensor.shape[0], batch_size):
-                a = batch_offset
-                b = min(a + batch_size, tensor.shape[0])
-                x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [tensor[a:b]], "c_concat": [image_cond_in[a:b]]})
-
-            x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond={"c_crossattn": [uncond], "c_concat": [image_cond_in[-uncond.shape[0]:]]})
-
-        devices.test_for_nans(x_out, "unet")
-
-        if opts.live_preview_content == "Prompt":
-            store_latent(x_out[0:uncond.shape[0]])
-        elif opts.live_preview_content == "Negative prompt":
-            store_latent(x_out[-uncond.shape[0]:])
-
-        denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
-
-        if self.mask is not None:
-            denoised = self.init_latent * self.mask + self.nmask * denoised
-
-        self.step += 1
-
-        return denoised
-
-
-class TorchHijack:
-    def __init__(self, sampler_noises):
-        # Using a deque to efficiently receive the sampler_noises in the same order as the previous index-based
-        # implementation.
-        self.sampler_noises = deque(sampler_noises)
-
-    def __getattr__(self, item):
-        if item == 'randn_like':
-            return self.randn_like
-
-        if hasattr(torch, item):
-            return getattr(torch, item)
-
-        raise AttributeError("'{}' object has no attribute '{}'".format(type(self).__name__, item))
-
-    def randn_like(self, x):
-        if self.sampler_noises:
-            noise = self.sampler_noises.popleft()
-            if noise.shape == x.shape:
-                return noise
-
-        if x.device.type == 'mps':
-            return torch.randn_like(x, device=devices.cpu).to(x.device)
-        else:
-            return torch.randn_like(x)
-
-
-# MPS fix for randn in torchsde
-def torchsde_randn(size, dtype, device, seed):
-    if device.type == 'mps':
-        generator = torch.Generator(devices.cpu).manual_seed(int(seed))
-        return torch.randn(size, dtype=dtype, device=devices.cpu, generator=generator).to(device)
-    else:
-        generator = torch.Generator(device).manual_seed(int(seed))
-        return torch.randn(size, dtype=dtype, device=device, generator=generator)
-
-
-torchsde._brownian.brownian_interval._randn = torchsde_randn
-
-
-class KDiffusionSampler:
-    def __init__(self, funcname, sd_model):
-        denoiser = k_diffusion.external.CompVisVDenoiser if sd_model.parameterization == "v" else k_diffusion.external.CompVisDenoiser
-
-        self.model_wrap = denoiser(sd_model, quantize=shared.opts.enable_quantization)
-        self.funcname = funcname
-        self.func = getattr(k_diffusion.sampling, self.funcname)
-        self.extra_params = sampler_extra_params.get(funcname, [])
-        self.model_wrap_cfg = CFGDenoiser(self.model_wrap)
-        self.sampler_noises = None
-        self.stop_at = None
-        self.eta = None
-        self.default_eta = 1.0
-        self.config = None
-        self.last_latent = None
-
-        self.conditioning_key = sd_model.model.conditioning_key
-
-    def callback_state(self, d):
-        step = d['i']
-        latent = d["denoised"]
-        if opts.live_preview_content == "Combined":
-            store_latent(latent)
-        self.last_latent = latent
-
-        if self.stop_at is not None and step > self.stop_at:
-            raise InterruptedException
-
-        state.sampling_step = step
-        shared.total_tqdm.update()
-
-    def launch_sampling(self, steps, func):
-        state.sampling_steps = steps
-        state.sampling_step = 0
-
-        try:
-            return func()
-        except InterruptedException:
-            return self.last_latent
-
-    def number_of_needed_noises(self, p):
-        return p.steps
-
-    def initialize(self, p):
-        self.model_wrap_cfg.mask = p.mask if hasattr(p, 'mask') else None
-        self.model_wrap_cfg.nmask = p.nmask if hasattr(p, 'nmask') else None
-        self.model_wrap_cfg.step = 0
-        self.eta = p.eta or opts.eta_ancestral
-
-        k_diffusion.sampling.torch = TorchHijack(self.sampler_noises if self.sampler_noises is not None else [])
-
-        extra_params_kwargs = {}
-        for param_name in self.extra_params:
-            if hasattr(p, param_name) and param_name in inspect.signature(self.func).parameters:
-                extra_params_kwargs[param_name] = getattr(p, param_name)
-
-        if 'eta' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['eta'] = self.eta
-
-        return extra_params_kwargs
-
-    def get_sigmas(self, p, steps):
-        discard_next_to_last_sigma = self.config is not None and self.config.options.get('discard_next_to_last_sigma', False)
-        if opts.always_discard_next_to_last_sigma and not discard_next_to_last_sigma:
-            discard_next_to_last_sigma = True
-            p.extra_generation_params["Discard penultimate sigma"] = True
-
-        steps += 1 if discard_next_to_last_sigma else 0
-
-        if p.sampler_noise_scheduler_override:
-            sigmas = p.sampler_noise_scheduler_override(steps)
-        elif self.config is not None and self.config.options.get('scheduler', None) == 'karras':
-            sigma_min, sigma_max = (0.1, 10) if opts.use_old_karras_scheduler_sigmas else (self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item())
-
-            sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=sigma_min, sigma_max=sigma_max, device=shared.device)
-        else:
-            sigmas = self.model_wrap.get_sigmas(steps)
-
-        if discard_next_to_last_sigma:
-            sigmas = torch.cat([sigmas[:-2], sigmas[-1:]])
-
-        return sigmas
-
-    def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
-        steps, t_enc = setup_img2img_steps(p, steps)
-
-        sigmas = self.get_sigmas(p, steps)
-
-        sigma_sched = sigmas[steps - t_enc - 1:]
-        xi = x + noise * sigma_sched[0]
-        
-        extra_params_kwargs = self.initialize(p)
-        if 'sigma_min' in inspect.signature(self.func).parameters:
-            ## last sigma is zero which isn't allowed by DPM Fast & Adaptive so taking value before last
-            extra_params_kwargs['sigma_min'] = sigma_sched[-2]
-        if 'sigma_max' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['sigma_max'] = sigma_sched[0]
-        if 'n' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['n'] = len(sigma_sched) - 1
-        if 'sigma_sched' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['sigma_sched'] = sigma_sched
-        if 'sigmas' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['sigmas'] = sigma_sched
-
-        self.model_wrap_cfg.init_latent = x
-        self.last_latent = x
-
-        samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args={
-            'cond': conditioning, 
-            'image_cond': image_conditioning, 
-            'uncond': unconditional_conditioning, 
-            'cond_scale': p.cfg_scale
-        }, disable=False, callback=self.callback_state, **extra_params_kwargs))
-
-        return samples
-
-    def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning = None):
-        steps = steps or p.steps
-
-        sigmas = self.get_sigmas(p, steps)
-
-        x = x * sigmas[0]
-
-        extra_params_kwargs = self.initialize(p)
-        if 'sigma_min' in inspect.signature(self.func).parameters:
-            extra_params_kwargs['sigma_min'] = self.model_wrap.sigmas[0].item()
-            extra_params_kwargs['sigma_max'] = self.model_wrap.sigmas[-1].item()
-            if 'n' in inspect.signature(self.func).parameters:
-                extra_params_kwargs['n'] = steps
-        else:
-            extra_params_kwargs['sigmas'] = sigmas
-
-        self.last_latent = x
-        samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
-            'cond': conditioning, 
-            'image_cond': image_conditioning, 
-            'uncond': unconditional_conditioning, 
-            'cond_scale': p.cfg_scale
-        }, disable=False, callback=self.callback_state, **extra_params_kwargs))
-
-        return samples
-

modules/sd_samplers_common.py

@@ -0,0 +1,62 @@
+from collections import namedtuple
+import numpy as np
+import torch
+from PIL import Image
+from modules import devices, processing, images, sd_vae_approx
+
+from modules.shared import opts, state
+import modules.shared as shared
+
+SamplerData = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options'])
+
+
+def setup_img2img_steps(p, steps=None):
+    if opts.img2img_fix_steps or steps is not None:
+        requested_steps = (steps or p.steps)
+        steps = int(requested_steps / min(p.denoising_strength, 0.999)) if p.denoising_strength > 0 else 0
+        t_enc = requested_steps - 1
+    else:
+        steps = p.steps
+        t_enc = int(min(p.denoising_strength, 0.999) * steps)
+
+    return steps, t_enc
+
+
+approximation_indexes = {"Full": 0, "Approx NN": 1, "Approx cheap": 2}
+
+
+def single_sample_to_image(sample, approximation=None):
+    if approximation is None:
+        approximation = approximation_indexes.get(opts.show_progress_type, 0)
+
+    if approximation == 2:
+        x_sample = sd_vae_approx.cheap_approximation(sample)
+    elif approximation == 1:
+        x_sample = sd_vae_approx.model()(sample.to(devices.device, devices.dtype).unsqueeze(0))[0].detach()
+    else:
+        x_sample = processing.decode_first_stage(shared.sd_model, sample.unsqueeze(0))[0]
+
+    x_sample = torch.clamp((x_sample + 1.0) / 2.0, min=0.0, max=1.0)
+    x_sample = 255. * np.moveaxis(x_sample.cpu().numpy(), 0, 2)
+    x_sample = x_sample.astype(np.uint8)
+    return Image.fromarray(x_sample)
+
+
+def sample_to_image(samples, index=0, approximation=None):
+    return single_sample_to_image(samples[index], approximation)
+
+
+def samples_to_image_grid(samples, approximation=None):
+    return images.image_grid([single_sample_to_image(sample, approximation) for sample in samples])
+
+
+def store_latent(decoded):
+    state.current_latent = decoded
+
+    if opts.live_previews_enable and opts.show_progress_every_n_steps > 0 and shared.state.sampling_step % opts.show_progress_every_n_steps == 0:
+        if not shared.parallel_processing_allowed:
+            shared.state.assign_current_image(sample_to_image(decoded))
+
+
+class InterruptedException(BaseException):
+    pass

modules/sd_samplers_compvis.py

@@ -0,0 +1,160 @@
+import math
+import ldm.models.diffusion.ddim
+import ldm.models.diffusion.plms
+
+import numpy as np
+import torch
+
+from modules.shared import state
+from modules import sd_samplers_common, prompt_parser, shared
+
+
+samplers_data_compvis = [
+    sd_samplers_common.SamplerData('DDIM', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.ddim.DDIMSampler, model), [], {}),
+    sd_samplers_common.SamplerData('PLMS', lambda model: VanillaStableDiffusionSampler(ldm.models.diffusion.plms.PLMSSampler, model), [], {}),
+]
+
+
+class VanillaStableDiffusionSampler:
+    def __init__(self, constructor, sd_model):
+        self.sampler = constructor(sd_model)
+        self.is_plms = hasattr(self.sampler, 'p_sample_plms')
+        self.orig_p_sample_ddim = self.sampler.p_sample_plms if self.is_plms else self.sampler.p_sample_ddim
+        self.mask = None
+        self.nmask = None
+        self.init_latent = None
+        self.sampler_noises = None
+        self.step = 0
+        self.stop_at = None
+        self.eta = None
+        self.config = None
+        self.last_latent = None
+
+        self.conditioning_key = sd_model.model.conditioning_key
+
+    def number_of_needed_noises(self, p):
+        return 0
+
+    def launch_sampling(self, steps, func):
+        state.sampling_steps = steps
+        state.sampling_step = 0
+
+        try:
+            return func()
+        except sd_samplers_common.InterruptedException:
+            return self.last_latent
+
+    def p_sample_ddim_hook(self, x_dec, cond, ts, unconditional_conditioning, *args, **kwargs):
+        if state.interrupted or state.skipped:
+            raise sd_samplers_common.InterruptedException
+
+        if self.stop_at is not None and self.step > self.stop_at:
+            raise sd_samplers_common.InterruptedException
+
+        # Have to unwrap the inpainting conditioning here to perform pre-processing
+        image_conditioning = None
+        if isinstance(cond, dict):
+            image_conditioning = cond["c_concat"][0]
+            cond = cond["c_crossattn"][0]
+            unconditional_conditioning = unconditional_conditioning["c_crossattn"][0]
+
+        conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
+        unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step)
+
+        assert all([len(conds) == 1 for conds in conds_list]), 'composition via AND is not supported for DDIM/PLMS samplers'
+        cond = tensor
+
+        # for DDIM, shapes must match, we can't just process cond and uncond independently;
+        # filling unconditional_conditioning with repeats of the last vector to match length is
+        # not 100% correct but should work well enough
+        if unconditional_conditioning.shape[1] < cond.shape[1]:
+            last_vector = unconditional_conditioning[:, -1:]
+            last_vector_repeated = last_vector.repeat([1, cond.shape[1] - unconditional_conditioning.shape[1], 1])
+            unconditional_conditioning = torch.hstack([unconditional_conditioning, last_vector_repeated])
+        elif unconditional_conditioning.shape[1] > cond.shape[1]:
+            unconditional_conditioning = unconditional_conditioning[:, :cond.shape[1]]
+
+        if self.mask is not None:
+            img_orig = self.sampler.model.q_sample(self.init_latent, ts)
+            x_dec = img_orig * self.mask + self.nmask * x_dec
+
+        # Wrap the image conditioning back up since the DDIM code can accept the dict directly.
+        # Note that they need to be lists because it just concatenates them later.
+        if image_conditioning is not None:
+            cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]}
+            unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
+
+        res = self.orig_p_sample_ddim(x_dec, cond, ts, unconditional_conditioning=unconditional_conditioning, *args, **kwargs)
+
+        if self.mask is not None:
+            self.last_latent = self.init_latent * self.mask + self.nmask * res[1]
+        else:
+            self.last_latent = res[1]
+
+        sd_samplers_common.store_latent(self.last_latent)
+
+        self.step += 1
+        state.sampling_step = self.step
+        shared.total_tqdm.update()
+
+        return res
+
+    def initialize(self, p):
+        self.eta = p.eta if p.eta is not None else shared.opts.eta_ddim
+        if self.eta != 0.0:
+            p.extra_generation_params["Eta DDIM"] = self.eta
+
+        for fieldname in ['p_sample_ddim', 'p_sample_plms']:
+            if hasattr(self.sampler, fieldname):
+                setattr(self.sampler, fieldname, self.p_sample_ddim_hook)
+
+        self.mask = p.mask if hasattr(p, 'mask') else None
+        self.nmask = p.nmask if hasattr(p, 'nmask') else None
+
+    def adjust_steps_if_invalid(self, p, num_steps):
+        if (self.config.name == 'DDIM' and p.ddim_discretize == 'uniform') or (self.config.name == 'PLMS'):
+            valid_step = 999 / (1000 // num_steps)
+            if valid_step == math.floor(valid_step):
+                return int(valid_step) + 1
+        
+        return num_steps
+
+    def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
+        steps, t_enc = sd_samplers_common.setup_img2img_steps(p, steps)
+        steps = self.adjust_steps_if_invalid(p, steps)
+        self.initialize(p)
+
+        self.sampler.make_schedule(ddim_num_steps=steps, ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False)
+        x1 = self.sampler.stochastic_encode(x, torch.tensor([t_enc] * int(x.shape[0])).to(shared.device), noise=noise)
+
+        self.init_latent = x
+        self.last_latent = x
+        self.step = 0
+
+        # Wrap the conditioning models with additional image conditioning for inpainting model
+        if image_conditioning is not None:
+            conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
+            unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
+
+        samples = self.launch_sampling(t_enc + 1, lambda: self.sampler.decode(x1, conditioning, t_enc, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning))
+
+        return samples
+
+    def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
+        self.initialize(p)
+
+        self.init_latent = None
+        self.last_latent = x
+        self.step = 0
+
+        steps = self.adjust_steps_if_invalid(p, steps or p.steps)
+
+        # Wrap the conditioning models with additional image conditioning for inpainting model
+        # dummy_for_plms is needed because PLMS code checks the first item in the dict to have the right shape
+        if image_conditioning is not None:
+            conditioning = {"dummy_for_plms": np.zeros((conditioning.shape[0],)), "c_crossattn": [conditioning], "c_concat": [image_conditioning]}
+            unconditional_conditioning = {"c_crossattn": [unconditional_conditioning], "c_concat": [image_conditioning]}
+
+        samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
+
+        return samples_ddim

modules/sd_samplers_kdiffusion.py

@@ -0,0 +1,331 @@
+from collections import deque
+import torch
+import inspect
+import einops
+import k_diffusion.sampling
+from modules import prompt_parser, devices, sd_samplers_common
+
+from modules.shared import opts, state
+import modules.shared as shared
+from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback
+
+samplers_k_diffusion = [
+    ('Euler a', 'sample_euler_ancestral', ['k_euler_a', 'k_euler_ancestral'], {}),
+    ('Euler', 'sample_euler', ['k_euler'], {}),
+    ('LMS', 'sample_lms', ['k_lms'], {}),
+    ('Heun', 'sample_heun', ['k_heun'], {}),
+    ('DPM2', 'sample_dpm_2', ['k_dpm_2'], {'discard_next_to_last_sigma': True}),
+    ('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {'discard_next_to_last_sigma': True}),
+    ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}),
+    ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),
+    ('DPM++ SDE', 'sample_dpmpp_sde', ['k_dpmpp_sde'], {}),
+    ('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}),
+    ('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}),
+    ('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),
+    ('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}),
+    ('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras', 'discard_next_to_last_sigma': True}),
+    ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}),
+    ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}),
+    ('DPM++ SDE Karras', 'sample_dpmpp_sde', ['k_dpmpp_sde_ka'], {'scheduler': 'karras'}),
+]
+
+samplers_data_k_diffusion = [
+    sd_samplers_common.SamplerData(label, lambda model, funcname=funcname: KDiffusionSampler(funcname, model), aliases, options)
+    for label, funcname, aliases, options in samplers_k_diffusion
+    if hasattr(k_diffusion.sampling, funcname)
+]
+
+sampler_extra_params = {
+    'sample_euler': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
+    'sample_heun': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
+    'sample_dpm_2': ['s_churn', 's_tmin', 's_tmax', 's_noise'],
+}
+
+
+class CFGDenoiser(torch.nn.Module):
+    """
+    Classifier free guidance denoiser. A wrapper for stable diffusion model (specifically for unet)
+    that can take a noisy picture and produce a noise-free picture using two guidances (prompts)
+    instead of one. Originally, the second prompt is just an empty string, but we use non-empty
+    negative prompt.
+    """
+
+    def __init__(self, model):
+        super().__init__()
+        self.inner_model = model
+        self.mask = None
+        self.nmask = None
+        self.init_latent = None
+        self.step = 0
+        self.image_cfg_scale = None
+
+    def combine_denoised(self, x_out, conds_list, uncond, cond_scale):
+        denoised_uncond = x_out[-uncond.shape[0]:]
+        denoised = torch.clone(denoised_uncond)
+
+        for i, conds in enumerate(conds_list):
+            for cond_index, weight in conds:
+                denoised[i] += (x_out[cond_index] - denoised_uncond[i]) * (weight * cond_scale)
+
+        return denoised
+
+    def combine_denoised_for_edit_model(self, x_out, cond_scale):
+        out_cond, out_img_cond, out_uncond = x_out.chunk(3)
+        denoised = out_uncond + cond_scale * (out_cond - out_img_cond) + self.image_cfg_scale * (out_img_cond - out_uncond)
+
+        return denoised
+
+    def forward(self, x, sigma, uncond, cond, cond_scale, image_cond):
+        if state.interrupted or state.skipped:
+            raise sd_samplers_common.InterruptedException
+
+        # at self.image_cfg_scale == 1.0 produced results for edit model are the same as with normal sampling,
+        # so is_edit_model is set to False to support AND composition.
+        is_edit_model = shared.sd_model.cond_stage_key == "edit" and self.image_cfg_scale is not None and self.image_cfg_scale != 1.0
+
+        conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
+        uncond = prompt_parser.reconstruct_cond_batch(uncond, self.step)
+
+        assert not is_edit_model or all([len(conds) == 1 for conds in conds_list]), "AND is not supported for InstructPix2Pix checkpoint (unless using Image CFG scale = 1.0)"
+
+        batch_size = len(conds_list)
+        repeats = [len(conds_list[i]) for i in range(batch_size)]
+
+        if not is_edit_model:
+            x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x])
+            sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
+            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
+        else:
+            x_in = torch.cat([torch.stack([x[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [x] + [x])
+            sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma] + [sigma])
+            image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond] + [torch.zeros_like(self.init_latent)])
+
+        denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)
+        cfg_denoiser_callback(denoiser_params)
+        x_in = denoiser_params.x
+        image_cond_in = denoiser_params.image_cond
+        sigma_in = denoiser_params.sigma
+
+        if tensor.shape[1] == uncond.shape[1]:
+            if not is_edit_model:
+                cond_in = torch.cat([tensor, uncond])
+            else:
+                cond_in = torch.cat([tensor, uncond, uncond])
+
+            if shared.batch_cond_uncond:
+                x_out = self.inner_model(x_in, sigma_in, cond={"c_crossattn": [cond_in], "c_concat": [image_cond_in]})
+            else:
+                x_out = torch.zeros_like(x_in)
+                for batch_offset in range(0, x_out.shape[0], batch_size):
+                    a = batch_offset
+                    b = a + batch_size
+                    x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": [cond_in[a:b]], "c_concat": [image_cond_in[a:b]]})
+        else:
+            x_out = torch.zeros_like(x_in)
+            batch_size = batch_size*2 if shared.batch_cond_uncond else batch_size
+            for batch_offset in range(0, tensor.shape[0], batch_size):
+                a = batch_offset
+                b = min(a + batch_size, tensor.shape[0])
+
+                if not is_edit_model:
+                    c_crossattn = [tensor[a:b]]
+                else:
+                    c_crossattn = torch.cat([tensor[a:b]], uncond)
+
+                x_out[a:b] = self.inner_model(x_in[a:b], sigma_in[a:b], cond={"c_crossattn": c_crossattn, "c_concat": [image_cond_in[a:b]]})
+
+            x_out[-uncond.shape[0]:] = self.inner_model(x_in[-uncond.shape[0]:], sigma_in[-uncond.shape[0]:], cond={"c_crossattn": [uncond], "c_concat": [image_cond_in[-uncond.shape[0]:]]})
+
+        devices.test_for_nans(x_out, "unet")
+
+        if opts.live_preview_content == "Prompt":
+            sd_samplers_common.store_latent(x_out[0:uncond.shape[0]])
+        elif opts.live_preview_content == "Negative prompt":
+            sd_samplers_common.store_latent(x_out[-uncond.shape[0]:])
+
+        if not is_edit_model:
+            denoised = self.combine_denoised(x_out, conds_list, uncond, cond_scale)
+        else:
+            denoised = self.combine_denoised_for_edit_model(x_out, cond_scale)
+
+        if self.mask is not None:
+            denoised = self.init_latent * self.mask + self.nmask * denoised
+
+        self.step += 1
+
+        return denoised
+
+
+class TorchHijack:
+    def __init__(self, sampler_noises):
+        # Using a deque to efficiently receive the sampler_noises in the same order as the previous index-based
+        # implementation.
+        self.sampler_noises = deque(sampler_noises)
+
+    def __getattr__(self, item):
+        if item == 'randn_like':
+            return self.randn_like
+
+        if hasattr(torch, item):
+            return getattr(torch, item)
+
+        raise AttributeError("'{}' object has no attribute '{}'".format(type(self).__name__, item))
+
+    def randn_like(self, x):
+        if self.sampler_noises:
+            noise = self.sampler_noises.popleft()
+            if noise.shape == x.shape:
+                return noise
+
+        if x.device.type == 'mps':
+            return torch.randn_like(x, device=devices.cpu).to(x.device)
+        else:
+            return torch.randn_like(x)
+
+
+class KDiffusionSampler:
+    def __init__(self, funcname, sd_model):
+        denoiser = k_diffusion.external.CompVisVDenoiser if sd_model.parameterization == "v" else k_diffusion.external.CompVisDenoiser
+
+        self.model_wrap = denoiser(sd_model, quantize=shared.opts.enable_quantization)
+        self.funcname = funcname
+        self.func = getattr(k_diffusion.sampling, self.funcname)
+        self.extra_params = sampler_extra_params.get(funcname, [])
+        self.model_wrap_cfg = CFGDenoiser(self.model_wrap)
+        self.sampler_noises = None
+        self.stop_at = None
+        self.eta = None
+        self.config = None
+        self.last_latent = None
+
+        self.conditioning_key = sd_model.model.conditioning_key
+
+    def callback_state(self, d):
+        step = d['i']
+        latent = d["denoised"]
+        if opts.live_preview_content == "Combined":
+            sd_samplers_common.store_latent(latent)
+        self.last_latent = latent
+
+        if self.stop_at is not None and step > self.stop_at:
+            raise sd_samplers_common.InterruptedException
+
+        state.sampling_step = step
+        shared.total_tqdm.update()
+
+    def launch_sampling(self, steps, func):
+        state.sampling_steps = steps
+        state.sampling_step = 0
+
+        try:
+            return func()
+        except sd_samplers_common.InterruptedException:
+            return self.last_latent
+
+    def number_of_needed_noises(self, p):
+        return p.steps
+
+    def initialize(self, p):
+        self.model_wrap_cfg.mask = p.mask if hasattr(p, 'mask') else None
+        self.model_wrap_cfg.nmask = p.nmask if hasattr(p, 'nmask') else None
+        self.model_wrap_cfg.step = 0
+        self.model_wrap_cfg.image_cfg_scale = getattr(p, 'image_cfg_scale', None)
+        self.eta = p.eta if p.eta is not None else opts.eta_ancestral
+
+        k_diffusion.sampling.torch = TorchHijack(self.sampler_noises if self.sampler_noises is not None else [])
+
+        extra_params_kwargs = {}
+        for param_name in self.extra_params:
+            if hasattr(p, param_name) and param_name in inspect.signature(self.func).parameters:
+                extra_params_kwargs[param_name] = getattr(p, param_name)
+
+        if 'eta' in inspect.signature(self.func).parameters:
+            if self.eta != 1.0:
+                p.extra_generation_params["Eta"] = self.eta
+
+            extra_params_kwargs['eta'] = self.eta
+
+        return extra_params_kwargs
+
+    def get_sigmas(self, p, steps):
+        discard_next_to_last_sigma = self.config is not None and self.config.options.get('discard_next_to_last_sigma', False)
+        if opts.always_discard_next_to_last_sigma and not discard_next_to_last_sigma:
+            discard_next_to_last_sigma = True
+            p.extra_generation_params["Discard penultimate sigma"] = True
+
+        steps += 1 if discard_next_to_last_sigma else 0
+
+        if p.sampler_noise_scheduler_override:
+            sigmas = p.sampler_noise_scheduler_override(steps)
+        elif self.config is not None and self.config.options.get('scheduler', None) == 'karras':
+            sigma_min, sigma_max = (0.1, 10) if opts.use_old_karras_scheduler_sigmas else (self.model_wrap.sigmas[0].item(), self.model_wrap.sigmas[-1].item())
+
+            sigmas = k_diffusion.sampling.get_sigmas_karras(n=steps, sigma_min=sigma_min, sigma_max=sigma_max, device=shared.device)
+        else:
+            sigmas = self.model_wrap.get_sigmas(steps)
+
+        if discard_next_to_last_sigma:
+            sigmas = torch.cat([sigmas[:-2], sigmas[-1:]])
+
+        return sigmas
+
+    def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
+        steps, t_enc = sd_samplers_common.setup_img2img_steps(p, steps)
+
+        sigmas = self.get_sigmas(p, steps)
+
+        sigma_sched = sigmas[steps - t_enc - 1:]
+        xi = x + noise * sigma_sched[0]
+        
+        extra_params_kwargs = self.initialize(p)
+        if 'sigma_min' in inspect.signature(self.func).parameters:
+            ## last sigma is zero which isn't allowed by DPM Fast & Adaptive so taking value before last
+            extra_params_kwargs['sigma_min'] = sigma_sched[-2]
+        if 'sigma_max' in inspect.signature(self.func).parameters:
+            extra_params_kwargs['sigma_max'] = sigma_sched[0]
+        if 'n' in inspect.signature(self.func).parameters:
+            extra_params_kwargs['n'] = len(sigma_sched) - 1
+        if 'sigma_sched' in inspect.signature(self.func).parameters:
+            extra_params_kwargs['sigma_sched'] = sigma_sched
+        if 'sigmas' in inspect.signature(self.func).parameters:
+            extra_params_kwargs['sigmas'] = sigma_sched
+
+        self.model_wrap_cfg.init_latent = x
+        self.last_latent = x
+        extra_args={
+            'cond': conditioning, 
+            'image_cond': image_conditioning, 
+            'uncond': unconditional_conditioning, 
+            'cond_scale': p.cfg_scale,
+        }
+
+        samples = self.launch_sampling(t_enc + 1, lambda: self.func(self.model_wrap_cfg, xi, extra_args=extra_args, disable=False, callback=self.callback_state, **extra_params_kwargs))
+
+        return samples
+
+    def sample(self, p, x, conditioning, unconditional_conditioning, steps=None, image_conditioning = None):
+        steps = steps or p.steps
+
+        sigmas = self.get_sigmas(p, steps)
+
+        x = x * sigmas[0]
+
+        extra_params_kwargs = self.initialize(p)
+        if 'sigma_min' in inspect.signature(self.func).parameters:
+            extra_params_kwargs['sigma_min'] = self.model_wrap.sigmas[0].item()
+            extra_params_kwargs['sigma_max'] = self.model_wrap.sigmas[-1].item()
+            if 'n' in inspect.signature(self.func).parameters:
+                extra_params_kwargs['n'] = steps
+        else:
+            extra_params_kwargs['sigmas'] = sigmas
+
+        self.last_latent = x
+        samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
+            'cond': conditioning, 
+            'image_cond': image_conditioning, 
+            'uncond': unconditional_conditioning, 
+            'cond_scale': p.cfg_scale
+        }, disable=False, callback=self.callback_state, **extra_params_kwargs))
+
+        return samples
+

modules/shared.py

@@ -105,6 +105,8 @@ parser.add_argument("--tls-keyfile", type=str, help="Partially enables TLS, requ
 parser.add_argument("--tls-certfile", type=str, help="Partially enables TLS, requires --tls-keyfile to fully function", default=None)
 parser.add_argument("--server-name", type=str, help="Sets hostname of server", default=None)
 parser.add_argument("--gradio-queue", action='store_true', help="Uses gradio queue; experimental option; breaks restart UI button")
+parser.add_argument("--skip-version-check", action='store_true', help="Do not check versions of torch and xformers")
+parser.add_argument("--no-hashing", action='store_true', help="disable sha256 hashing of checkpoints to help loading performance", default=False)
 
 
 script_loading.preload_extensions(extensions.extensions_dir, parser)
@@ -127,12 +129,13 @@ restricted_opts = {
 ui_reorder_categories = [
     "inpaint",
     "sampler",
+    "checkboxes",
+    "hires_fix",
     "dimensions",
     "cfg",
     "seed",
-    "checkboxes",
-    "hires_fix",
     "batch",
+    "override_settings",
     "scripts",
 ]
 
@@ -324,7 +327,7 @@ options_templates.update(options_section(('saving-images', "Saving images/grids"
     "jpeg_quality": OptionInfo(80, "Quality for saved jpeg images", gr.Slider, {"minimum": 1, "maximum": 100, "step": 1}),
     "export_for_4chan": OptionInfo(True, "If PNG image is larger than 4MB or any dimension is larger than 4000, downscale and save copy as JPG"),
 
-    "use_original_name_batch": OptionInfo(False, "Use original name for output filename during batch process in extras tab"),
+    "use_original_name_batch": OptionInfo(True, "Use original name for output filename during batch process in extras tab"),
     "use_upscaler_name_as_suffix": OptionInfo(False, "Use upscaler name as filename suffix in the extras tab"),
     "save_selected_only": OptionInfo(True, "When using 'Save' button, only save a single selected image"),
     "do_not_add_watermark": OptionInfo(False, "Do not add watermark to images"),
@@ -346,10 +349,10 @@ options_templates.update(options_section(('saving-paths', "Paths for saving"), {
 }))
 
 options_templates.update(options_section(('saving-to-dirs', "Saving to a directory"), {
-    "save_to_dirs": OptionInfo(False, "Save images to a subdirectory"),
+    "save_to_dirs": OptionInfo(True, "Save images to a subdirectory"),
-    "grid_save_to_dirs": OptionInfo(False, "Save grids to a subdirectory"),
+    "grid_save_to_dirs": OptionInfo(True, "Save grids to a subdirectory"),
     "use_save_to_dirs_for_ui": OptionInfo(False, "When using \"Save\" button, save images to a subdirectory"),
-    "directories_filename_pattern": OptionInfo("", "Directory name pattern", component_args=hide_dirs),
+    "directories_filename_pattern": OptionInfo("[date]", "Directory name pattern", component_args=hide_dirs),
     "directories_max_prompt_words": OptionInfo(8, "Max prompt words for [prompt_words] pattern", gr.Slider, {"minimum": 1, "maximum": 20, "step": 1, **hide_dirs}),
 }))
 
@@ -440,7 +443,7 @@ options_templates.update(options_section(('ui', "User interface"), {
     "do_not_show_images": OptionInfo(False, "Do not show any images in results for web"),
     "add_model_hash_to_info": OptionInfo(True, "Add model hash to generation information"),
     "add_model_name_to_info": OptionInfo(True, "Add model name to generation information"),
-    "disable_weights_auto_swap": OptionInfo(False, "When reading generation parameters from text into UI (from PNG info or pasted text), do not change the selected model/checkpoint."),
+    "disable_weights_auto_swap": OptionInfo(True, "When reading generation parameters from text into UI (from PNG info or pasted text), do not change the selected model/checkpoint."),
     "send_seed": OptionInfo(True, "Send seed when sending prompt or image to other interface"),
     "send_size": OptionInfo(True, "Send size when sending prompt or image to another interface"),
     "font": OptionInfo("", "Font for image grids that have text"),
@@ -605,11 +608,37 @@ class Options:
 
         self.data_labels = {k: v for k, v in sorted(settings_items, key=lambda x: section_ids[x[1].section])}
 
+    def cast_value(self, key, value):
+        """casts an arbitrary to the same type as this setting's value with key
+        Example: cast_value("eta_noise_seed_delta", "12") -> returns 12 (an int rather than str)
+        """
+
+        if value is None:
+            return None
+
+        default_value = self.data_labels[key].default
+        if default_value is None:
+            default_value = getattr(self, key, None)
+        if default_value is None:
+            return None
+
+        expected_type = type(default_value)
+        if expected_type == bool and value == "False":
+            value = False
+        else:
+            value = expected_type(value)
+
+        return value
+
+
 
 opts = Options()
 if os.path.exists(config_filename):
     opts.load(config_filename)
 
+settings_components = None
+"""assinged from ui.py, a mapping on setting anmes to gradio components repsponsible for those settings"""
+
 latent_upscale_default_mode = "Latent"
 latent_upscale_modes = {
     "Latent": {"mode": "bilinear", "antialias": False},

modules/txt2img.py

@@ -1,5 +1,6 @@
 import modules.scripts
 from modules import sd_samplers
+from modules.generation_parameters_copypaste import create_override_settings_dict
 from modules.processing import StableDiffusionProcessing, Processed, StableDiffusionProcessingTxt2Img, \
     StableDiffusionProcessingImg2Img, process_images
 from modules.shared import opts, cmd_opts
@@ -8,7 +9,9 @@ import modules.processing as processing
 from modules.ui import plaintext_to_html
 
 
-def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, *args):
+def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, steps: int, sampler_index: int, restore_faces: bool, tiling: bool, n_iter: int, batch_size: int, cfg_scale: float, seed: int, subseed: int, subseed_strength: float, seed_resize_from_h: int, seed_resize_from_w: int, seed_enable_extras: bool, height: int, width: int, enable_hr: bool, denoising_strength: float, hr_scale: float, hr_upscaler: str, hr_second_pass_steps: int, hr_resize_x: int, hr_resize_y: int, override_settings_texts, *args):
+    override_settings = create_override_settings_dict(override_settings_texts)
+
     p = StableDiffusionProcessingTxt2Img(
         sd_model=shared.sd_model,
         outpath_samples=opts.outdir_samples or opts.outdir_txt2img_samples,
@@ -38,6 +41,7 @@ def txt2img(id_task: str, prompt: str, negative_prompt: str, prompt_styles, step
         hr_second_pass_steps=hr_second_pass_steps,
         hr_resize_x=hr_resize_x,
         hr_resize_y=hr_resize_y,
+        override_settings=override_settings,
     )
 
     p.scripts = modules.scripts.scripts_txt2img

modules/ui.py

@@ -380,6 +380,7 @@ def apply_setting(key, value):
     opts.save(shared.config_filename)
     return getattr(opts, key)
 
+
 def create_refresh_button(refresh_component, refresh_method, refreshed_args, elem_id):
     def refresh():
         refresh_method()
@@ -433,6 +434,18 @@ def get_value_for_setting(key):
     return gr.update(value=value, **args)
 
 
+def create_override_settings_dropdown(tabname, row):
+    dropdown = gr.Dropdown([], label="Override settings", visible=False, elem_id=f"{tabname}_override_settings", multiselect=True)
+
+    dropdown.change(
+        fn=lambda x: gr.Dropdown.update(visible=len(x) > 0),
+        inputs=[dropdown],
+        outputs=[dropdown],
+    )
+
+    return dropdown
+
+
 def create_ui():
     import modules.img2img
     import modules.txt2img
@@ -466,8 +479,8 @@ def create_ui():
                                 width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="txt2img_width")
                                 height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="txt2img_height")
 
+                            res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="txt2img_res_switch_btn")
                             if opts.dimensions_and_batch_together:
-                                res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="txt2img_res_switch_btn")
                                 with gr.Column(elem_id="txt2img_column_batch"):
                                     batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="txt2img_batch_count")
                                     batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
@@ -503,6 +516,10 @@ def create_ui():
                                 batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="txt2img_batch_count")
                                 batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="txt2img_batch_size")
 
+                    elif category == "override_settings":
+                        with FormRow(elem_id="txt2img_override_settings_row") as row:
+                            override_settings = create_override_settings_dropdown('txt2img', row)
+
                     elif category == "scripts":
                         with FormGroup(elem_id="txt2img_script_container"):
                             custom_inputs = modules.scripts.scripts_txt2img.setup_ui()
@@ -524,7 +541,6 @@ def create_ui():
                 )
 
             txt2img_gallery, generation_info, html_info, html_log = create_output_panel("txt2img", opts.outdir_txt2img_samples)
-            parameters_copypaste.bind_buttons({"txt2img": txt2img_paste}, None, txt2img_prompt)
 
             connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False)
             connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True)
@@ -555,6 +571,7 @@ def create_ui():
                     hr_second_pass_steps,
                     hr_resize_x,
                     hr_resize_y,
+                    override_settings,
                 ] + custom_inputs,
 
                 outputs=[
@@ -615,6 +632,9 @@ def create_ui():
                 *modules.scripts.scripts_txt2img.infotext_fields
             ]
             parameters_copypaste.add_paste_fields("txt2img", None, txt2img_paste_fields)
+            parameters_copypaste.register_paste_params_button(parameters_copypaste.ParamBinding(
+                paste_button=txt2img_paste, tabname="txt2img", source_text_component=txt2img_prompt, source_image_component=None, override_settings_component=override_settings,
+            ))
 
             txt2img_preview_params = [
                 txt2img_prompt,
@@ -737,15 +757,17 @@ def create_ui():
                                 width = gr.Slider(minimum=64, maximum=2048, step=8, label="Width", value=512, elem_id="img2img_width")
                                 height = gr.Slider(minimum=64, maximum=2048, step=8, label="Height", value=512, elem_id="img2img_height")
 
+                            res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="img2img_res_switch_btn")
                             if opts.dimensions_and_batch_together:
-                                res_switch_btn = ToolButton(value=switch_values_symbol, elem_id="img2img_res_switch_btn")
                                 with gr.Column(elem_id="img2img_column_batch"):
                                     batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
                                     batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
 
                     elif category == "cfg":
                         with FormGroup():
-                            cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="img2img_cfg_scale")
+                            with FormRow():
+                                cfg_scale = gr.Slider(minimum=1.0, maximum=30.0, step=0.5, label='CFG Scale', value=7.0, elem_id="img2img_cfg_scale")
+                                image_cfg_scale = gr.Slider(minimum=0, maximum=3.0, step=0.05, label='Image CFG Scale', value=1.5, elem_id="img2img_image_cfg_scale", visible=shared.sd_model and shared.sd_model.cond_stage_key == "edit")
                             denoising_strength = gr.Slider(minimum=0.0, maximum=1.0, step=0.01, label='Denoising strength', value=0.75, elem_id="img2img_denoising_strength")
 
                     elif category == "seed":
@@ -762,6 +784,10 @@ def create_ui():
                                 batch_count = gr.Slider(minimum=1, step=1, label='Batch count', value=1, elem_id="img2img_batch_count")
                                 batch_size = gr.Slider(minimum=1, maximum=8, step=1, label='Batch size', value=1, elem_id="img2img_batch_size")
 
+                    elif category == "override_settings":
+                        with FormRow(elem_id="img2img_override_settings_row") as row:
+                            override_settings = create_override_settings_dropdown('img2img', row)
+
                     elif category == "scripts":
                         with FormGroup(elem_id="img2img_script_container"):
                             custom_inputs = modules.scripts.scripts_img2img.setup_ui()
@@ -796,7 +822,6 @@ def create_ui():
                                 )
 
             img2img_gallery, generation_info, html_info, html_log = create_output_panel("img2img", opts.outdir_img2img_samples)
-            parameters_copypaste.bind_buttons({"img2img": img2img_paste}, None, img2img_prompt)
 
             connect_reuse_seed(seed, reuse_seed, generation_info, dummy_component, is_subseed=False)
             connect_reuse_seed(subseed, reuse_subseed, generation_info, dummy_component, is_subseed=True)
@@ -838,6 +863,7 @@ def create_ui():
                     batch_count,
                     batch_size,
                     cfg_scale,
+                    image_cfg_scale,
                     denoising_strength,
                     seed,
                     subseed, subseed_strength, seed_resize_from_h, seed_resize_from_w, seed_checkbox,
@@ -849,7 +875,8 @@ def create_ui():
                     inpainting_mask_invert,
                     img2img_batch_input_dir,
                     img2img_batch_output_dir,
-                    img2img_batch_inpaint_mask_dir
+                    img2img_batch_inpaint_mask_dir,
+                    override_settings,
                 ] + custom_inputs,
                 outputs=[
                     img2img_gallery,
@@ -923,6 +950,7 @@ def create_ui():
                 (sampler_index, "Sampler"),
                 (restore_faces, "Face restoration"),
                 (cfg_scale, "CFG scale"),
+                (image_cfg_scale, "Image CFG scale"),
                 (seed, "Seed"),
                 (width, "Size-1"),
                 (height, "Size-2"),
@@ -937,6 +965,9 @@ def create_ui():
             ]
             parameters_copypaste.add_paste_fields("img2img", init_img, img2img_paste_fields)
             parameters_copypaste.add_paste_fields("inpaint", init_img_with_mask, img2img_paste_fields)
+            parameters_copypaste.register_paste_params_button(parameters_copypaste.ParamBinding(
+                paste_button=img2img_paste, tabname="img2img", source_text_component=img2img_prompt, source_image_component=None, override_settings_component=override_settings,
+            ))
 
     modules.scripts.scripts_current = None
 
@@ -954,7 +985,11 @@ def create_ui():
                 html2 = gr.HTML()
                 with gr.Row():
                     buttons = parameters_copypaste.create_buttons(["txt2img", "img2img", "inpaint", "extras"])
-                parameters_copypaste.bind_buttons(buttons, image, generation_info)
+
+                for tabname, button in buttons.items():
+                    parameters_copypaste.register_paste_params_button(parameters_copypaste.ParamBinding(
+                        paste_button=button, tabname=tabname, source_text_component=generation_info, source_image_component=image,
+                    ))
 
         image.change(
             fn=wrap_gradio_call(modules.extras.run_pnginfo),
@@ -1363,6 +1398,7 @@ def create_ui():
 
     components = []
     component_dict = {}
+    shared.settings_components = component_dict
 
     script_callbacks.ui_settings_callback()
     opts.reorder()
@@ -1529,8 +1565,7 @@ def create_ui():
                 component = create_setting_component(k, is_quicksettings=True)
                 component_dict[k] = component
 
-        parameters_copypaste.integrate_settings_paste_fields(component_dict)
+        parameters_copypaste.connect_paste_params_buttons()
-        parameters_copypaste.run_bind()
 
         with gr.Tabs(elem_id="tabs") as tabs:
             for interface, label, ifid in interfaces:
@@ -1560,6 +1595,12 @@ def create_ui():
                 outputs=[component, text_settings],
             )
 
+        text_settings.change(
+            fn=lambda: gr.update(visible=shared.sd_model and shared.sd_model.cond_stage_key == "edit"),
+            inputs=[],
+            outputs=[image_cfg_scale],
+        )
+
         button_set_checkpoint = gr.Button('Change checkpoint', elem_id='change_checkpoint', visible=False)
         button_set_checkpoint.click(
             fn=lambda value, _: run_settings_single(value, key='sd_model_checkpoint'),

modules/ui_common.py

@@ -198,5 +198,9 @@ Requested path was: {f}
                 html_info = gr.HTML(elem_id=f'html_info_{tabname}')
                 html_log = gr.HTML(elem_id=f'html_log_{tabname}')
 
-            parameters_copypaste.bind_buttons(buttons, result_gallery, "txt2img" if tabname == "txt2img" else None)
+            for paste_tabname, paste_button in buttons.items():
+                parameters_copypaste.register_paste_params_button(parameters_copypaste.ParamBinding(
+                    paste_button=paste_button, tabname=paste_tabname, source_tabname="txt2img" if tabname == "txt2img" else None, source_image_component=result_gallery
+                ))
+
             return result_gallery, generation_info if tabname != "extras" else html_info_x, html_info, html_log

modules/ui_extra_networks.py

@@ -26,11 +26,12 @@ def add_pages_to_demo(app):
     def fetch_file(filename: str = ""):
         from starlette.responses import FileResponse
 
-        if not any([Path(x).resolve() in Path(filename).resolve().parents for x in allowed_dirs]):
+        if not any([Path(x).absolute() in Path(filename).absolute().parents for x in allowed_dirs]):
             raise ValueError(f"File cannot be fetched: {filename}. Must be in one of directories registered by extra pages.")
 
-        if os.path.splitext(filename)[1].lower() != ".png":
+        ext = os.path.splitext(filename)[1].lower()
-            raise ValueError(f"File cannot be fetched: {filename}. Only png.")
+        if ext not in (".png", ".jpg"):
+            raise ValueError(f"File cannot be fetched: {filename}. Only png and jpg.")
 
         # would profit from returning 304
         return FileResponse(filename, headers={"Accept-Ranges": "bytes"})

modules/ui_extra_networks_checkpoints.py

@@ -14,6 +14,7 @@ class ExtraNetworksPageCheckpoints(ui_extra_networks.ExtraNetworksPage):
         shared.refresh_checkpoints()
 
     def list_items(self):
+        checkpoint: sd_models.CheckpointInfo
         for name, checkpoint in sd_models.checkpoints_list.items():
             path, ext = os.path.splitext(checkpoint.filename)
             previews = [path + ".png", path + ".preview.png"]
@@ -28,7 +29,7 @@ class ExtraNetworksPageCheckpoints(ui_extra_networks.ExtraNetworksPage):
                 "name": checkpoint.name_for_extra,
                 "filename": path,
                 "preview": preview,
-                "search_term": self.search_terms_from_path(checkpoint.filename),
+                "search_term": self.search_terms_from_path(checkpoint.filename) + " " + (checkpoint.sha256 or ""),
                 "onclick": '"' + html.escape(f"""return selectCheckpoint({json.dumps(name)})""") + '"',
                 "local_preview": path + ".png",
             }

scripts/img2imgalt.py

@@ -6,7 +6,7 @@ from tqdm import trange
 import modules.scripts as scripts
 import gradio as gr
 
-from modules import processing, shared, sd_samplers, prompt_parser
+from modules import processing, shared, sd_samplers, prompt_parser, sd_samplers_common
 from modules.processing import Processed
 from modules.shared import opts, cmd_opts, state
 
@@ -50,7 +50,7 @@ def find_noise_for_image(p, cond, uncond, cfg_scale, steps):
 
         x = x + d * dt
 
-        sd_samplers.store_latent(x)
+        sd_samplers_common.store_latent(x)
 
         # This shouldn't be necessary, but solved some VRAM issues
         del x_in, sigma_in, cond_in, c_out, c_in, t,
@@ -104,7 +104,7 @@ def find_noise_for_image_sigma_adjustment(p, cond, uncond, cfg_scale, steps):
         dt = sigmas[i] - sigmas[i - 1]
         x = x + d * dt
 
-        sd_samplers.store_latent(x)
+        sd_samplers_common.store_latent(x)
 
         # This shouldn't be necessary, but solved some VRAM issues
         del x_in, sigma_in, cond_in, c_out, c_in, t,

scripts/prompt_matrix.py

@@ -45,15 +45,33 @@ class Script(scripts.Script):
         return "Prompt matrix"
 
     def ui(self, is_img2img):
-        put_at_start = gr.Checkbox(label='Put variable parts at start of prompt', value=False, elem_id=self.elem_id("put_at_start"))
+        gr.HTML('<br />')
-        different_seeds = gr.Checkbox(label='Use different seed for each picture', value=False, elem_id=self.elem_id("different_seeds"))
+        with gr.Row():
+            with gr.Column():
+                put_at_start = gr.Checkbox(label='Put variable parts at start of prompt', value=False, elem_id=self.elem_id("put_at_start"))
+                different_seeds = gr.Checkbox(label='Use different seed for each picture', value=False, elem_id=self.elem_id("different_seeds"))
+            with gr.Column():
+                prompt_type = gr.Radio(["positive", "negative"], label="Select prompt", elem_id=self.elem_id("prompt_type"), value="positive")
+                variations_delimiter = gr.Radio(["comma", "space"], label="Select joining char", elem_id=self.elem_id("variations_delimiter"), value="comma")
+            with gr.Column():
+                margin_size = gr.Slider(label="Grid margins (px)", min=0, max=500, value=0, step=2, elem_id=self.elem_id("margin_size"))
 
-        return [put_at_start, different_seeds]
+        return [put_at_start, different_seeds, prompt_type, variations_delimiter, margin_size]
 
-    def run(self, p, put_at_start, different_seeds):
+    def run(self, p, put_at_start, different_seeds, prompt_type, variations_delimiter, margin_size):
         modules.processing.fix_seed(p)
+        # Raise error if promp type is not positive or negative
+        if prompt_type not in ["positive", "negative"]:
+            raise ValueError(f"Unknown prompt type {prompt_type}")
+        # Raise error if variations delimiter is not comma or space
+        if variations_delimiter not in ["comma", "space"]:
+            raise ValueError(f"Unknown variations delimiter {variations_delimiter}")
 
-        original_prompt = p.prompt[0] if type(p.prompt) == list else p.prompt
+        prompt = p.prompt if prompt_type == "positive" else p.negative_prompt
+        original_prompt = prompt[0] if type(prompt) == list else prompt
+        positive_prompt = p.prompt[0] if type(p.prompt) == list else p.prompt
+
+        delimiter = ", " if variations_delimiter == "comma" else " "
 
         all_prompts = []
         prompt_matrix_parts = original_prompt.split("|")
@@ -66,20 +84,23 @@ class Script(scripts.Script):
             else:
                 selected_prompts = [prompt_matrix_parts[0]] + selected_prompts
 
-            all_prompts.append(", ".join(selected_prompts))
+            all_prompts.append(delimiter.join(selected_prompts))
 
         p.n_iter = math.ceil(len(all_prompts) / p.batch_size)
         p.do_not_save_grid = True
 
         print(f"Prompt matrix will create {len(all_prompts)} images using a total of {p.n_iter} batches.")
 
-        p.prompt = all_prompts
+        if prompt_type == "positive":
+            p.prompt = all_prompts
+        else:
+            p.negative_prompt = all_prompts
         p.seed = [p.seed + (i if different_seeds else 0) for i in range(len(all_prompts))]
-        p.prompt_for_display = original_prompt
+        p.prompt_for_display = positive_prompt
         processed = process_images(p)
 
         grid = images.image_grid(processed.images, p.batch_size, rows=1 << ((len(prompt_matrix_parts) - 1) // 2))
-        grid = images.draw_prompt_matrix(grid, p.width, p.height, prompt_matrix_parts)
+        grid = images.draw_prompt_matrix(grid, p.width, p.height, prompt_matrix_parts, margin_size)
         processed.images.insert(0, grid)
         processed.index_of_first_image = 1
         processed.infotexts.insert(0, processed.infotexts[0])

scripts/xyz_grid.py

@@ -205,7 +205,7 @@ axis_options = [
 ]
 
 
-def draw_xyz_grid(p, xs, ys, zs, x_labels, y_labels, z_labels, cell, draw_legend, include_lone_images, include_sub_grids, first_axes_processed, second_axes_processed):
+def draw_xyz_grid(p, xs, ys, zs, x_labels, y_labels, z_labels, cell, draw_legend, include_lone_images, include_sub_grids, first_axes_processed, second_axes_processed, margin_size):
     hor_texts = [[images.GridAnnotation(x)] for x in x_labels]
     ver_texts = [[images.GridAnnotation(y)] for y in y_labels]
     title_texts = [[images.GridAnnotation(z)] for z in z_labels]
@@ -286,23 +286,24 @@ def draw_xyz_grid(p, xs, ys, zs, x_labels, y_labels, z_labels, cell, draw_legend
         print("Unexpected error: draw_xyz_grid failed to return even a single processed image")
         return Processed(p, [])
 
-    grids = [None] * len(zs)
+    sub_grids = [None] * len(zs)
     for i in range(len(zs)):
         start_index = i * len(xs) * len(ys)
         end_index = start_index + len(xs) * len(ys)
         grid = images.image_grid(image_cache[start_index:end_index], rows=len(ys))
         if draw_legend:
-            grid = images.draw_grid_annotations(grid, cell_size[0], cell_size[1], hor_texts, ver_texts)
+            grid = images.draw_grid_annotations(grid, cell_size[0], cell_size[1], hor_texts, ver_texts, margin_size)
-        
+        sub_grids[i] = grid
-        grids[i] = grid        
         if include_sub_grids and len(zs) > 1:
             processed_result.images.insert(i+1, grid)
 
-    original_grid_size = grids[0].size
+    sub_grid_size = sub_grids[0].size
-    grids = images.image_grid(grids, rows=1)
+    z_grid = images.image_grid(sub_grids, rows=1)
-    processed_result.images[0] = images.draw_grid_annotations(grids, original_grid_size[0], original_grid_size[1], title_texts, [[images.GridAnnotation()]])
+    if draw_legend:
+        z_grid = images.draw_grid_annotations(z_grid, sub_grid_size[0], sub_grid_size[1], title_texts, [[images.GridAnnotation()]])
+    processed_result.images[0] = z_grid
 
-    return processed_result
+    return processed_result, sub_grids
 
 
 class SharedSettingsStackHelper(object):
@@ -350,10 +351,16 @@ class Script(scripts.Script):
                     fill_z_button = ToolButton(value=fill_values_symbol, elem_id="xyz_grid_fill_z_tool_button", visible=False)
 
         with gr.Row(variant="compact", elem_id="axis_options"):
-            draw_legend = gr.Checkbox(label='Draw legend', value=True, elem_id=self.elem_id("draw_legend"))
+            with gr.Column():
-            include_lone_images = gr.Checkbox(label='Include Sub Images', value=False, elem_id=self.elem_id("include_lone_images"))
+                draw_legend = gr.Checkbox(label='Draw legend', value=True, elem_id=self.elem_id("draw_legend"))
-            include_sub_grids = gr.Checkbox(label='Include Sub Grids', value=False, elem_id=self.elem_id("include_sub_grids"))
+                no_fixed_seeds = gr.Checkbox(label='Keep -1 for seeds', value=False, elem_id=self.elem_id("no_fixed_seeds"))
-            no_fixed_seeds = gr.Checkbox(label='Keep -1 for seeds', value=False, elem_id=self.elem_id("no_fixed_seeds"))
+            with gr.Column():
+                include_lone_images = gr.Checkbox(label='Include Sub Images', value=False, elem_id=self.elem_id("include_lone_images"))
+                include_sub_grids = gr.Checkbox(label='Include Sub Grids', value=False, elem_id=self.elem_id("include_sub_grids"))
+            with gr.Column():
+                margin_size = gr.Slider(label="Grid margins (px)", min=0, max=500, value=0, step=2, elem_id=self.elem_id("margin_size"))
+        
+        with gr.Row(variant="compact", elem_id="swap_axes"):
             swap_xy_axes_button = gr.Button(value="Swap X/Y axes", elem_id="xy_grid_swap_axes_button")
             swap_yz_axes_button = gr.Button(value="Swap Y/Z axes", elem_id="yz_grid_swap_axes_button")
             swap_xz_axes_button = gr.Button(value="Swap X/Z axes", elem_id="xz_grid_swap_axes_button")
@@ -392,9 +399,9 @@ class Script(scripts.Script):
             (z_values, "Z Values"),
         )
 
-        return [x_type, x_values, y_type, y_values, z_type, z_values, draw_legend, include_lone_images, include_sub_grids, no_fixed_seeds]
+        return [x_type, x_values, y_type, y_values, z_type, z_values, draw_legend, include_lone_images, include_sub_grids, no_fixed_seeds, margin_size]
 
-    def run(self, p, x_type, x_values, y_type, y_values, z_type, z_values, draw_legend, include_lone_images, include_sub_grids, no_fixed_seeds):
+    def run(self, p, x_type, x_values, y_type, y_values, z_type, z_values, draw_legend, include_lone_images, include_sub_grids, no_fixed_seeds, margin_size):
         if not no_fixed_seeds:
             modules.processing.fix_seed(p)
 
@@ -576,7 +583,7 @@ class Script(scripts.Script):
             return res
 
         with SharedSettingsStackHelper():
-            processed = draw_xyz_grid(
+            processed, sub_grids = draw_xyz_grid(
                 p,
                 xs=xs,
                 ys=ys,
@@ -589,9 +596,14 @@ class Script(scripts.Script):
                 include_lone_images=include_lone_images,
                 include_sub_grids=include_sub_grids,
                 first_axes_processed=first_axes_processed,
-                second_axes_processed=second_axes_processed
+                second_axes_processed=second_axes_processed,
+                margin_size=margin_size
             )
 
+        if opts.grid_save and len(sub_grids) > 1:
+            for sub_grid in sub_grids:
+                images.save_image(sub_grid, p.outpath_grids, "xyz_grid", info=grid_infotext[0], extension=opts.grid_format, prompt=p.prompt, seed=processed.seed, grid=True, p=p)
+
         if opts.grid_save:
             images.save_image(processed.images[0], p.outpath_grids, "xyz_grid", info=grid_infotext[0], extension=opts.grid_format, prompt=p.prompt, seed=processed.seed, grid=True, p=p)
 

webui.py

@@ -52,6 +52,9 @@ else:
 
 
 def check_versions():
+    if shared.cmd_opts.skip_version_check:
+        return
+
     expected_torch_version = "1.13.1"
 
     if version.parse(torch.__version__) < version.parse(expected_torch_version):
@@ -59,7 +62,10 @@ def check_versions():
 You are running torch {torch.__version__}.
 The program is tested to work with torch {expected_torch_version}.
 To reinstall the desired version, run with commandline flag --reinstall-torch.
-Beware that this will cause a lot of large files to be downloaded.
+Beware that this will cause a lot of large files to be downloaded, as well as
+there are reports of issues with training tab on the latest version.
+
+Use --skip-version-check commandline argument to disable this check.
         """.strip())
 
     expected_xformers_version = "0.0.16rc425"
@@ -71,6 +77,8 @@ Beware that this will cause a lot of large files to be downloaded.
 You are running xformers {xformers.__version__}.
 The program is tested to work with xformers {expected_xformers_version}.
 To reinstall the desired version, run with commandline flag --reinstall-xformers.
+
+Use --skip-version-check commandline argument to disable this check.
             """.strip())