split oversize extras.py to postprocessing.py

modules/extras.py

@@ -1,231 +1,16 @@
-from __future__ import annotations
-import math
 import os
 import re
-import sys
-import traceback
 import shutil
 
-import numpy as np
-from PIL import Image
 
 import torch
 import tqdm
 
-from typing import Callable, List, OrderedDict, Tuple
+from modules import shared, images, sd_models, sd_vae
-from functools import partial
-from dataclasses import dataclass
-
-from modules import processing, shared, images, devices, sd_models, sd_samplers, sd_vae
-from modules.shared import opts
-import modules.gfpgan_model
 from modules.ui import plaintext_to_html
-import modules.codeformer_model
 import gradio as gr
 import safetensors.torch
 
-class LruCache(OrderedDict):
-    @dataclass(frozen=True)
-    class Key:
-        image_hash: int
-        info_hash: int
-        args_hash: int
-
-    @dataclass
-    class Value:
-        image: Image.Image
-        info: str
-
-    def __init__(self, max_size: int = 5, *args, **kwargs):
-        super().__init__(*args, **kwargs)
-        self._max_size = max_size
-
-    def get(self, key: LruCache.Key) -> LruCache.Value:
-        ret = super().get(key)
-        if ret is not None:
-            self.move_to_end(key)  # Move to end of eviction list
-        return ret
-
-    def put(self, key: LruCache.Key, value: LruCache.Value) -> None:
-        self[key] = value
-        while len(self) > self._max_size:
-            self.popitem(last=False)
-
-
-cached_images: LruCache = LruCache(max_size=5)
-
-
-def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_dir, show_extras_results, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility, upscale_first: bool, save_output: bool = True):
-    devices.torch_gc()
-
-    shared.state.begin()
-    shared.state.job = 'extras'
-
-    imageArr = []
-    # Also keep track of original file names
-    imageNameArr = []
-    outputs = []
-
-    if extras_mode == 1:
-        #convert file to pillow image
-        for img in image_folder:
-            image = Image.open(img)
-            imageArr.append(image)
-            imageNameArr.append(os.path.splitext(img.orig_name)[0])
-    elif extras_mode == 2:
-        assert not shared.cmd_opts.hide_ui_dir_config, '--hide-ui-dir-config option must be disabled'
-
-        if input_dir == '':
-            return outputs, "Please select an input directory.", ''
-        image_list = shared.listfiles(input_dir)
-        for img in image_list:
-            try:
-                image = Image.open(img)
-            except Exception:
-                continue
-            imageArr.append(image)
-            imageNameArr.append(img)
-    else:
-        imageArr.append(image)
-        imageNameArr.append(None)
-
-    if extras_mode == 2 and output_dir != '':
-        outpath = output_dir
-    else:
-        outpath = opts.outdir_samples or opts.outdir_extras_samples
-
-    # Extra operation definitions
-
-    def run_gfpgan(image: Image.Image, info: str) -> Tuple[Image.Image, str]:
-        shared.state.job = 'extras-gfpgan'
-        restored_img = modules.gfpgan_model.gfpgan_fix_faces(np.array(image, dtype=np.uint8))
-        res = Image.fromarray(restored_img)
-
-        if gfpgan_visibility < 1.0:
-            res = Image.blend(image, res, gfpgan_visibility)
-
-        info += f"GFPGAN visibility:{round(gfpgan_visibility, 2)}\n"
-        return (res, info)
-
-    def run_codeformer(image: Image.Image, info: str) -> Tuple[Image.Image, str]:
-        shared.state.job = 'extras-codeformer'
-        restored_img = modules.codeformer_model.codeformer.restore(np.array(image, dtype=np.uint8), w=codeformer_weight)
-        res = Image.fromarray(restored_img)
-
-        if codeformer_visibility < 1.0:
-            res = Image.blend(image, res, codeformer_visibility)
-
-        info += f"CodeFormer w: {round(codeformer_weight, 2)}, CodeFormer visibility:{round(codeformer_visibility, 2)}\n"
-        return (res, info)
-
-    def upscale(image, scaler_index, resize, mode, resize_w, resize_h, crop):
-        shared.state.job = 'extras-upscale'
-        upscaler = shared.sd_upscalers[scaler_index]
-        res = upscaler.scaler.upscale(image, resize, upscaler.data_path)
-        if mode == 1 and crop:
-            cropped = Image.new("RGB", (resize_w, resize_h))
-            cropped.paste(res, box=(resize_w // 2 - res.width // 2, resize_h // 2 - res.height // 2))
-            res = cropped
-        return res
-
-    def run_prepare_crop(image: Image.Image, info: str) -> Tuple[Image.Image, str]:
-        # Actual crop happens in run_upscalers_blend, this just sets upscaling_resize and adds info text
-        nonlocal upscaling_resize
-        if resize_mode == 1:
-            upscaling_resize = max(upscaling_resize_w/image.width, upscaling_resize_h/image.height)
-            crop_info = " (crop)" if upscaling_crop else ""
-            info += f"Resize to: {upscaling_resize_w:g}x{upscaling_resize_h:g}{crop_info}\n"
-        return (image, info)
-
-    @dataclass
-    class UpscaleParams:
-        upscaler_idx: int
-        blend_alpha: float
-
-    def run_upscalers_blend(params: List[UpscaleParams], image: Image.Image, info: str) -> Tuple[Image.Image, str]:
-        blended_result: Image.Image = None
-        image_hash: str = hash(np.array(image.getdata()).tobytes())
-        for upscaler in params:
-            upscale_args = (upscaler.upscaler_idx, upscaling_resize, resize_mode,
-                            upscaling_resize_w, upscaling_resize_h, upscaling_crop)
-            cache_key = LruCache.Key(image_hash=image_hash,
-                                     info_hash=hash(info),
-                                     args_hash=hash(upscale_args))
-            cached_entry = cached_images.get(cache_key)
-            if cached_entry is None:
-                res = upscale(image, *upscale_args)
-                info += f"Upscale: {round(upscaling_resize, 3)}, visibility: {upscaler.blend_alpha}, model:{shared.sd_upscalers[upscaler.upscaler_idx].name}\n"
-                cached_images.put(cache_key, LruCache.Value(image=res, info=info))
-            else:
-                res, info = cached_entry.image, cached_entry.info
-
-            if blended_result is None:
-                blended_result = res
-            else:
-                blended_result = Image.blend(blended_result, res, upscaler.blend_alpha)
-        return (blended_result, info)
-
-    # Build a list of operations to run
-    facefix_ops: List[Callable] = []
-    facefix_ops += [run_gfpgan] if gfpgan_visibility > 0 else []
-    facefix_ops += [run_codeformer] if codeformer_visibility > 0 else []
-
-    upscale_ops: List[Callable] = []
-    upscale_ops += [run_prepare_crop] if resize_mode == 1 else []
-
-    if upscaling_resize != 0:
-        step_params: List[UpscaleParams] = []
-        step_params.append(UpscaleParams(upscaler_idx=extras_upscaler_1, blend_alpha=1.0))
-        if extras_upscaler_2 != 0 and extras_upscaler_2_visibility > 0:
-            step_params.append(UpscaleParams(upscaler_idx=extras_upscaler_2, blend_alpha=extras_upscaler_2_visibility))
-
-        upscale_ops.append(partial(run_upscalers_blend, step_params))
-
-    extras_ops: List[Callable] = (upscale_ops + facefix_ops) if upscale_first else (facefix_ops + upscale_ops)
-
-    for image, image_name in zip(imageArr, imageNameArr):
-        if image is None:
-            return outputs, "Please select an input image.", ''
-
-        shared.state.textinfo = f'Processing image {image_name}'
-        
-        existing_pnginfo = image.info or {}
-
-        image = image.convert("RGB")
-        info = ""
-        # Run each operation on each image
-        for op in extras_ops:
-            image, info = op(image, info)
-
-        if opts.use_original_name_batch and image_name is not None:
-            basename = os.path.splitext(os.path.basename(image_name))[0]
-        else:
-            basename = ''
-
-        if opts.enable_pnginfo: # append info before save
-            image.info = existing_pnginfo
-            image.info["extras"] = info
-
-        if save_output:
-            # Add upscaler name as a suffix.
-            suffix = f"-{shared.sd_upscalers[extras_upscaler_1].name}" if shared.opts.use_upscaler_name_as_suffix else ""
-            # Add second upscaler if applicable.
-            if suffix and extras_upscaler_2 and extras_upscaler_2_visibility:
-                suffix += f"-{shared.sd_upscalers[extras_upscaler_2].name}"
-
-            images.save_image(image, path=outpath, basename=basename, seed=None, prompt=None, extension=opts.samples_format, info=info, short_filename=True,
-                            no_prompt=True, grid=False, pnginfo_section_name="extras", existing_info=existing_pnginfo, forced_filename=None, suffix=suffix)
-
-        if extras_mode != 2 or show_extras_results :
-            outputs.append(image)
-
-    devices.torch_gc()
-
-    return outputs, plaintext_to_html(info), ''
-
-def clear_cache():
-    cached_images.clear()
-
 
 def run_pnginfo(image):
     if image is None:

modules/postprocessing.py

@@ -1,28 +1,18 @@
 from __future__ import annotations
-import math
 import os
-import re
-import sys
-import traceback
-import shutil
 
 import numpy as np
 from PIL import Image
 
-import torch
-import tqdm
-
 from typing import Callable, List, OrderedDict, Tuple
 from functools import partial
 from dataclasses import dataclass
 
-from modules import processing, shared, images, devices, sd_models, sd_samplers, sd_vae
+from modules import shared, images, devices, ui_components
 from modules.shared import opts
 import modules.gfpgan_model
-from modules.ui import plaintext_to_html
 import modules.codeformer_model
-import gradio as gr
+
-import safetensors.torch
 
 class LruCache(OrderedDict):
     @dataclass(frozen=True)
@@ -55,7 +45,7 @@ class LruCache(OrderedDict):
 cached_images: LruCache = LruCache(max_size=5)
 
 
-def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_dir, show_extras_results, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility, upscale_first: bool, save_output: bool = True):
+def run_postprocessing(extras_mode, resize_mode, image, image_folder, input_dir, output_dir, show_extras_results, gfpgan_visibility, codeformer_visibility, codeformer_weight, upscaling_resize, upscaling_resize_w, upscaling_resize_h, upscaling_crop, extras_upscaler_1, extras_upscaler_2, extras_upscaler_2_visibility, upscale_first: bool, save_output: bool = True):
     devices.torch_gc()
 
     shared.state.begin()
@@ -221,246 +211,9 @@ def run_extras(extras_mode, resize_mode, image, image_folder, input_dir, output_
 
     devices.torch_gc()
 
-    return outputs, plaintext_to_html(info), ''
+    return outputs, ui_components.plaintext_to_html(info), ''
+
 
 def clear_cache():
     cached_images.clear()
 
-
-def run_pnginfo(image):
-    if image is None:
-        return '', '', ''
-
-    geninfo, items = images.read_info_from_image(image)
-    items = {**{'parameters': geninfo}, **items}
-
-    info = ''
-    for key, text in items.items():
-        info += f"""
-<div>
-<p><b>{plaintext_to_html(str(key))}</b></p>
-<p>{plaintext_to_html(str(text))}</p>
-</div>
-""".strip()+"\n"
-
-    if len(info) == 0:
-        message = "Nothing found in the image."
-        info = f"<div><p>{message}<p></div>"
-
-    return '', geninfo, info
-
-
-def create_config(ckpt_result, config_source, a, b, c):
-    def config(x):
-        res = sd_models.find_checkpoint_config(x) if x else None
-        return res if res != shared.sd_default_config else None
-
-    if config_source == 0:
-        cfg = config(a) or config(b) or config(c)
-    elif config_source == 1:
-        cfg = config(b)
-    elif config_source == 2:
-        cfg = config(c)
-    else:
-        cfg = None
-
-    if cfg is None:
-        return
-
-    filename, _ = os.path.splitext(ckpt_result)
-    checkpoint_filename = filename + ".yaml"
-
-    print("Copying config:")
-    print("   from:", cfg)
-    print("     to:", checkpoint_filename)
-    shutil.copyfile(cfg, checkpoint_filename)
-
-
-checkpoint_dict_skip_on_merge = ["cond_stage_model.transformer.text_model.embeddings.position_ids"]
-
-
-def to_half(tensor, enable):
-    if enable and tensor.dtype == torch.float:
-        return tensor.half()
-
-    return tensor
-
-
-def run_modelmerger(id_task, primary_model_name, secondary_model_name, tertiary_model_name, interp_method, multiplier, save_as_half, custom_name, checkpoint_format, config_source, bake_in_vae, discard_weights):
-    shared.state.begin()
-    shared.state.job = 'model-merge'
-
-    def fail(message):
-        shared.state.textinfo = message
-        shared.state.end()
-        return [*[gr.update() for _ in range(4)], message]
-
-    def weighted_sum(theta0, theta1, alpha):
-        return ((1 - alpha) * theta0) + (alpha * theta1)
-
-    def get_difference(theta1, theta2):
-        return theta1 - theta2
-
-    def add_difference(theta0, theta1_2_diff, alpha):
-        return theta0 + (alpha * theta1_2_diff)
-
-    def filename_weighted_sum():
-        a = primary_model_info.model_name
-        b = secondary_model_info.model_name
-        Ma = round(1 - multiplier, 2)
-        Mb = round(multiplier, 2)
-
-        return f"{Ma}({a}) + {Mb}({b})"
-
-    def filename_add_difference():
-        a = primary_model_info.model_name
-        b = secondary_model_info.model_name
-        c = tertiary_model_info.model_name
-        M = round(multiplier, 2)
-
-        return f"{a} + {M}({b} - {c})"
-
-    def filename_nothing():
-        return primary_model_info.model_name
-
-    theta_funcs = {
-        "Weighted sum": (filename_weighted_sum, None, weighted_sum),
-        "Add difference": (filename_add_difference, get_difference, add_difference),
-        "No interpolation": (filename_nothing, None, None),
-    }
-    filename_generator, theta_func1, theta_func2 = theta_funcs[interp_method]
-    shared.state.job_count = (1 if theta_func1 else 0) + (1 if theta_func2 else 0)
-
-    if not primary_model_name:
-        return fail("Failed: Merging requires a primary model.")
-
-    primary_model_info = sd_models.checkpoints_list[primary_model_name]
-
-    if theta_func2 and not secondary_model_name:
-        return fail("Failed: Merging requires a secondary model.")
-
-    secondary_model_info = sd_models.checkpoints_list[secondary_model_name] if theta_func2 else None
-
-    if theta_func1 and not tertiary_model_name:
-        return fail(f"Failed: Interpolation method ({interp_method}) requires a tertiary model.")
-
-    tertiary_model_info = sd_models.checkpoints_list[tertiary_model_name] if theta_func1 else None
-
-    result_is_inpainting_model = False
-
-    if theta_func2:
-        shared.state.textinfo = f"Loading B"
-        print(f"Loading {secondary_model_info.filename}...")
-        theta_1 = sd_models.read_state_dict(secondary_model_info.filename, map_location='cpu')
-    else:
-        theta_1 = None
-
-    if theta_func1:
-        shared.state.textinfo = f"Loading C"
-        print(f"Loading {tertiary_model_info.filename}...")
-        theta_2 = sd_models.read_state_dict(tertiary_model_info.filename, map_location='cpu')
-
-        shared.state.textinfo = 'Merging B and C'
-        shared.state.sampling_steps = len(theta_1.keys())
-        for key in tqdm.tqdm(theta_1.keys()):
-            if key in checkpoint_dict_skip_on_merge:
-                continue
-
-            if 'model' in key:
-                if key in theta_2:
-                    t2 = theta_2.get(key, torch.zeros_like(theta_1[key]))
-                    theta_1[key] = theta_func1(theta_1[key], t2)
-                else:
-                    theta_1[key] = torch.zeros_like(theta_1[key])
-
-            shared.state.sampling_step += 1
-        del theta_2
-
-        shared.state.nextjob()
-
-    shared.state.textinfo = f"Loading {primary_model_info.filename}..."
-    print(f"Loading {primary_model_info.filename}...")
-    theta_0 = sd_models.read_state_dict(primary_model_info.filename, map_location='cpu')
-
-    print("Merging...")
-    shared.state.textinfo = 'Merging A and B'
-    shared.state.sampling_steps = len(theta_0.keys())
-    for key in tqdm.tqdm(theta_0.keys()):
-        if theta_1 and 'model' in key and key in theta_1:
-
-            if key in checkpoint_dict_skip_on_merge:
-                continue
-
-            a = theta_0[key]
-            b = theta_1[key]
-
-            # this enables merging an inpainting model (A) with another one (B);
-            # where normal model would have 4 channels, for latenst space, inpainting model would
-            # have another 4 channels for unmasked picture's latent space, plus one channel for mask, for a total of 9
-            if a.shape != b.shape and a.shape[0:1] + a.shape[2:] == b.shape[0:1] + b.shape[2:]:
-                if a.shape[1] == 4 and b.shape[1] == 9:
-                    raise RuntimeError("When merging inpainting model with a normal one, A must be the inpainting model.")
-
-                assert a.shape[1] == 9 and b.shape[1] == 4, f"Bad dimensions for merged layer {key}: A={a.shape}, B={b.shape}"
-
-                theta_0[key][:, 0:4, :, :] = theta_func2(a[:, 0:4, :, :], b, multiplier)
-                result_is_inpainting_model = True
-            else:
-                theta_0[key] = theta_func2(a, b, multiplier)
-
-            theta_0[key] = to_half(theta_0[key], save_as_half)
-
-        shared.state.sampling_step += 1
-
-    del theta_1
-
-    bake_in_vae_filename = sd_vae.vae_dict.get(bake_in_vae, None)
-    if bake_in_vae_filename is not None:
-        print(f"Baking in VAE from {bake_in_vae_filename}")
-        shared.state.textinfo = 'Baking in VAE'
-        vae_dict = sd_vae.load_vae_dict(bake_in_vae_filename, map_location='cpu')
-
-        for key in vae_dict.keys():
-            theta_0_key = 'first_stage_model.' + key
-            if theta_0_key in theta_0:
-                theta_0[theta_0_key] = to_half(vae_dict[key], save_as_half)
-
-        del vae_dict
-
-    if save_as_half and not theta_func2:
-        for key in theta_0.keys():
-            theta_0[key] = to_half(theta_0[key], save_as_half)
-
-    if discard_weights:
-        regex = re.compile(discard_weights)
-        for key in list(theta_0):
-            if re.search(regex, key):
-                theta_0.pop(key, None)
-
-    ckpt_dir = shared.cmd_opts.ckpt_dir or sd_models.model_path
-
-    filename = filename_generator() if custom_name == '' else custom_name
-    filename += ".inpainting" if result_is_inpainting_model else ""
-    filename += "." + checkpoint_format
-
-    output_modelname = os.path.join(ckpt_dir, filename)
-
-    shared.state.nextjob()
-    shared.state.textinfo = "Saving"
-    print(f"Saving to {output_modelname}...")
-
-    _, extension = os.path.splitext(output_modelname)
-    if extension.lower() == ".safetensors":
-        safetensors.torch.save_file(theta_0, output_modelname, metadata={"format": "pt"})
-    else:
-        torch.save(theta_0, output_modelname)
-
-    sd_models.list_models()
-
-    create_config(output_modelname, config_source, primary_model_info, secondary_model_info, tertiary_model_info)
-
-    print(f"Checkpoint saved to {output_modelname}.")
-    shared.state.textinfo = "Checkpoint saved"
-    shared.state.end()
-
-    return [*[gr.Dropdown.update(choices=sd_models.checkpoint_tiles()) for _ in range(4)], "Checkpoint saved to " + output_modelname]

modules/ui.py

@@ -20,7 +20,7 @@ import numpy as np
 from PIL import Image, PngImagePlugin
 from modules.call_queue import wrap_gradio_gpu_call, wrap_queued_call, wrap_gradio_call
 
-from modules import sd_hijack, sd_models, localization, script_callbacks, ui_extensions, deepbooru, sd_vae, extra_networks
+from modules import sd_hijack, sd_models, localization, script_callbacks, ui_extensions, deepbooru, sd_vae, extra_networks, postprocessing, ui_components
 from modules.ui_components import FormRow, FormGroup, ToolButton, FormHTML
 from modules.paths import script_path
 
@@ -95,8 +95,8 @@ extra_networks_symbol = '\U0001F3B4'  # 🎴
 
 
 def plaintext_to_html(text):
-    text = "<p>" + "<br>\n".join([f"{html.escape(x)}" for x in text.split('\n')]) + "</p>"
+    return ui_components.plaintext_to_html(text)
-    return text
+
 
 def send_gradio_gallery_to_image(x):
     if len(x) == 0:
@@ -1152,7 +1152,7 @@ def create_ui():
             result_images, html_info_x, html_info, html_log = create_output_panel("extras", opts.outdir_extras_samples)
 
         submit.click(
-            fn=wrap_gradio_gpu_call(modules.extras.run_extras, extra_outputs=[None, '']),
+            fn=wrap_gradio_gpu_call(postprocessing.run_postprocessing, extra_outputs=[None, '']),
             _js="get_extras_tab_index",
             inputs=[
                 dummy_component,
@@ -1183,7 +1183,7 @@ def create_ui():
         parameters_copypaste.add_paste_fields("extras", extras_image, None)
 
         extras_image.change(
-            fn=modules.extras.clear_cache,
+            fn=postprocessing.clear_cache,
             inputs=[], outputs=[]
         )
 

modules/ui_components.py

@@ -1,3 +1,5 @@
+import html
+
 import gradio as gr
 
 
@@ -47,3 +49,8 @@ class FormColorPicker(gr.ColorPicker, gr.components.FormComponent):
 
     def get_block_name(self):
         return "colorpicker"
+
+
+def plaintext_to_html(text):
+    text = "<p>" + "<br>\n".join([f"{html.escape(x)}" for x in text.split('\n')]) + "</p>"
+    return text

webui.py

@@ -22,7 +22,6 @@ if ".dev" in torch.__version__ or "+git" in torch.__version__:
 
 from modules import shared, devices, sd_samplers, upscaler, extensions, localization, ui_tempdir, ui_extra_networks
 import modules.codeformer_model as codeformer
-import modules.extras
 import modules.face_restoration
 import modules.gfpgan_model as gfpgan
 import modules.img2img