remove the need to place configs near models
AUTOMATIC
parent
7a14c8ab45
commit
d2ac95fa7b
@ -0,0 +1,99 @@
|
||||
# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
|
||||
# See more details in LICENSE.
|
||||
|
||||
model:
|
||||
base_learning_rate: 1.0e-04
|
||||
target: modules.models.diffusion.ddpm_edit.LatentDiffusion
|
||||
params:
|
||||
linear_start: 0.00085
|
||||
linear_end: 0.0120
|
||||
num_timesteps_cond: 1
|
||||
log_every_t: 200
|
||||
timesteps: 1000
|
||||
first_stage_key: edited
|
||||
cond_stage_key: edit
|
||||
# image_size: 64
|
||||
# image_size: 32
|
||||
image_size: 16
|
||||
channels: 4
|
||||
cond_stage_trainable: false # Note: different from the one we trained before
|
||||
conditioning_key: hybrid
|
||||
monitor: val/loss_simple_ema
|
||||
scale_factor: 0.18215
|
||||
use_ema: true
|
||||
load_ema: true
|
||||
|
||||
scheduler_config: # 10000 warmup steps
|
||||
target: ldm.lr_scheduler.LambdaLinearScheduler
|
||||
params:
|
||||
warm_up_steps: [ 0 ]
|
||||
cycle_lengths: [ 10000000000000 ] # incredibly large number to prevent corner cases
|
||||
f_start: [ 1.e-6 ]
|
||||
f_max: [ 1. ]
|
||||
f_min: [ 1. ]
|
||||
|
||||
unet_config:
|
||||
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
||||
params:
|
||||
image_size: 32 # unused
|
||||
in_channels: 8
|
||||
out_channels: 4
|
||||
model_channels: 320
|
||||
attention_resolutions: [ 4, 2, 1 ]
|
||||
num_res_blocks: 2
|
||||
channel_mult: [ 1, 2, 4, 4 ]
|
||||
num_heads: 8
|
||||
use_spatial_transformer: True
|
||||
transformer_depth: 1
|
||||
context_dim: 768
|
||||
use_checkpoint: True
|
||||
legacy: False
|
||||
|
||||
first_stage_config:
|
||||
target: ldm.models.autoencoder.AutoencoderKL
|
||||
params:
|
||||
embed_dim: 4
|
||||
monitor: val/rec_loss
|
||||
ddconfig:
|
||||
double_z: true
|
||||
z_channels: 4
|
||||
resolution: 256
|
||||
in_channels: 3
|
||||
out_ch: 3
|
||||
ch: 128
|
||||
ch_mult:
|
||||
- 1
|
||||
- 2
|
||||
- 4
|
||||
- 4
|
||||
num_res_blocks: 2
|
||||
attn_resolutions: []
|
||||
dropout: 0.0
|
||||
lossconfig:
|
||||
target: torch.nn.Identity
|
||||
|
||||
cond_stage_config:
|
||||
target: ldm.modules.encoders.modules.FrozenCLIPEmbedder
|
||||
|
||||
data:
|
||||
target: main.DataModuleFromConfig
|
||||
params:
|
||||
batch_size: 128
|
||||
num_workers: 1
|
||||
wrap: false
|
||||
validation:
|
||||
target: edit_dataset.EditDataset
|
||||
params:
|
||||
path: data/clip-filtered-dataset
|
||||
cache_dir: data/
|
||||
cache_name: data_10k
|
||||
split: val
|
||||
min_text_sim: 0.2
|
||||
min_image_sim: 0.75
|
||||
min_direction_sim: 0.2
|
||||
max_samples_per_prompt: 1
|
||||
min_resize_res: 512
|
||||
max_resize_res: 512
|
||||
crop_res: 512
|
||||
output_as_edit: False
|
||||
real_input: True
|
||||
@ -0,0 +1,65 @@
|
||||
import re
|
||||
import os
|
||||
|
||||
from modules import shared, paths
|
||||
|
||||
sd_configs_path = shared.sd_configs_path
|
||||
sd_repo_configs_path = os.path.join(paths.paths['Stable Diffusion'], "configs", "stable-diffusion")
|
||||
|
||||
|
||||
config_default = shared.sd_default_config
|
||||
config_sd2 = os.path.join(sd_repo_configs_path, "v2-inference.yaml")
|
||||
config_sd2v = os.path.join(sd_repo_configs_path, "v2-inference-v.yaml")
|
||||
config_inpainting = os.path.join(sd_configs_path, "v1-inpainting-inference.yaml")
|
||||
config_instruct_pix2pix = os.path.join(sd_configs_path, "instruct-pix2pix.yaml")
|
||||
config_alt_diffusion = os.path.join(sd_configs_path, "alt-diffusion-inference.yaml")
|
||||
|
||||
re_parametrization_v = re.compile(r'-v\b')
|
||||
|
||||
|
||||
def guess_model_config_from_state_dict(sd, filename):
|
||||
fn = os.path.basename(filename)
|
||||
|
||||
sd2_cond_proj_weight = sd.get('cond_stage_model.model.transformer.resblocks.0.attn.in_proj_weight', None)
|
||||
diffusion_model_input = sd.get('model.diffusion_model.input_blocks.0.0.weight', None)
|
||||
roberta_weight = sd.get('cond_stage_model.roberta.embeddings.word_embeddings.weight', None)
|
||||
|
||||
if sd2_cond_proj_weight is not None and sd2_cond_proj_weight.shape[1] == 1024:
|
||||
if re.search(re_parametrization_v, fn) or "v2-1_768" in fn:
|
||||
return config_sd2v
|
||||
else:
|
||||
return config_sd2
|
||||
|
||||
if diffusion_model_input is not None:
|
||||
if diffusion_model_input.shape[1] == 9:
|
||||
return config_inpainting
|
||||
if diffusion_model_input.shape[1] == 8:
|
||||
return config_instruct_pix2pix
|
||||
|
||||
if roberta_weight is not None:
|
||||
return config_alt_diffusion
|
||||
|
||||
return config_default
|
||||
|
||||
|
||||
def find_checkpoint_config(state_dict, info):
|
||||
if info is None:
|
||||
return guess_model_config_from_state_dict(state_dict, "")
|
||||
|
||||
config = find_checkpoint_config_near_filename(info)
|
||||
if config is not None:
|
||||
return config
|
||||
|
||||
return guess_model_config_from_state_dict(state_dict, info.filename)
|
||||
|
||||
|
||||
def find_checkpoint_config_near_filename(info):
|
||||
if info is None:
|
||||
return None
|
||||
|
||||
config = os.path.splitext(info.filename)[0] + ".yaml"
|
||||
if os.path.exists(config):
|
||||
return config
|
||||
|
||||
return None
|
||||
|
||||
@ -0,0 +1,35 @@
|
||||
import time
|
||||
|
||||
|
||||
class Timer:
|
||||
def __init__(self):
|
||||
self.start = time.time()
|
||||
self.records = {}
|
||||
self.total = 0
|
||||
|
||||
def elapsed(self):
|
||||
end = time.time()
|
||||
res = end - self.start
|
||||
self.start = end
|
||||
return res
|
||||
|
||||
def record(self, category, extra_time=0):
|
||||
e = self.elapsed()
|
||||
if category not in self.records:
|
||||
self.records[category] = 0
|
||||
|
||||
self.records[category] += e + extra_time
|
||||
self.total += e + extra_time
|
||||
|
||||
def summary(self):
|
||||
res = f"{self.total:.1f}s"
|
||||
|
||||
additions = [x for x in self.records.items() if x[1] >= 0.1]
|
||||
if not additions:
|
||||
return res
|
||||
|
||||
res += " ("
|
||||
res += ", ".join([f"{category}: {time_taken:.1f}s" for category, time_taken in additions])
|
||||
res += ")"
|
||||
|
||||
return res
|
||||
Loading…
Reference in New Issue