mirror of
https://github.com/openvinotoolkit/stable-diffusion-webui.git
synced 2024-12-15 07:03:06 +03:00
Muhammad Rizqi Nur
parent
a27d19de2e
commit
ab05a74ead
@ -398,112 +398,110 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
|
||||
forced_filename = "<none>"
|
||||
|
||||
pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step)
|
||||
|
||||
try:
|
||||
for i, entries in pbar:
|
||||
hypernetwork.step = i + ititial_step
|
||||
if len(loss_dict) > 0:
|
||||
previous_mean_losses = [i[-1] for i in loss_dict.values()]
|
||||
previous_mean_loss = mean(previous_mean_losses)
|
||||
|
||||
scheduler.apply(optimizer, hypernetwork.step)
|
||||
if scheduler.finished:
|
||||
break
|
||||
|
||||
if shared.state.interrupted:
|
||||
break
|
||||
|
||||
with torch.autocast("cuda"):
|
||||
c = stack_conds([entry.cond for entry in entries]).to(devices.device)
|
||||
# c = torch.vstack([entry.cond for entry in entries]).to(devices.device)
|
||||
x = torch.stack([entry.latent for entry in entries]).to(devices.device)
|
||||
loss = shared.sd_model(x, c)[0]
|
||||
del x
|
||||
del c
|
||||
|
||||
losses[hypernetwork.step % losses.shape[0]] = loss.item()
|
||||
for entry in entries:
|
||||
loss_dict[entry.filename].append(loss.item())
|
||||
|
||||
optimizer.zero_grad()
|
||||
weights[0].grad = None
|
||||
loss.backward()
|
||||
|
||||
if weights[0].grad is None:
|
||||
steps_without_grad += 1
|
||||
else:
|
||||
steps_without_grad = 0
|
||||
assert steps_without_grad < 10, 'no gradient found for the trained weight after backward() for 10 steps in a row; this is a bug; training cannot continue'
|
||||
|
||||
optimizer.step()
|
||||
|
||||
steps_done = hypernetwork.step + 1
|
||||
|
||||
if torch.isnan(losses[hypernetwork.step % losses.shape[0]]):
|
||||
raise RuntimeError("Loss diverged.")
|
||||
for i, entries in pbar:
|
||||
hypernetwork.step = i + ititial_step
|
||||
if len(loss_dict) > 0:
|
||||
previous_mean_losses = [i[-1] for i in loss_dict.values()]
|
||||
previous_mean_loss = mean(previous_mean_losses)
|
||||
|
||||
if len(previous_mean_losses) > 1:
|
||||
std = stdev(previous_mean_losses)
|
||||
scheduler.apply(optimizer, hypernetwork.step)
|
||||
if scheduler.finished:
|
||||
break
|
||||
|
||||
if shared.state.interrupted:
|
||||
break
|
||||
|
||||
with torch.autocast("cuda"):
|
||||
c = stack_conds([entry.cond for entry in entries]).to(devices.device)
|
||||
# c = torch.vstack([entry.cond for entry in entries]).to(devices.device)
|
||||
x = torch.stack([entry.latent for entry in entries]).to(devices.device)
|
||||
loss = shared.sd_model(x, c)[0]
|
||||
del x
|
||||
del c
|
||||
|
||||
losses[hypernetwork.step % losses.shape[0]] = loss.item()
|
||||
for entry in entries:
|
||||
loss_dict[entry.filename].append(loss.item())
|
||||
|
||||
optimizer.zero_grad()
|
||||
weights[0].grad = None
|
||||
loss.backward()
|
||||
|
||||
if weights[0].grad is None:
|
||||
steps_without_grad += 1
|
||||
else:
|
||||
std = 0
|
||||
dataset_loss_info = f"dataset loss:{mean(previous_mean_losses):.3f}" + u"\u00B1" + f"({std / (len(previous_mean_losses) ** 0.5):.3f})"
|
||||
pbar.set_description(dataset_loss_info)
|
||||
steps_without_grad = 0
|
||||
assert steps_without_grad < 10, 'no gradient found for the trained weight after backward() for 10 steps in a row; this is a bug; training cannot continue'
|
||||
|
||||
if hypernetwork_dir is not None and steps_done % save_hypernetwork_every == 0:
|
||||
# Before saving, change name to match current checkpoint.
|
||||
hypernetwork.name = f'{hypernetwork_name}-{steps_done}'
|
||||
last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork.name}.pt')
|
||||
hypernetwork.save(last_saved_file)
|
||||
optimizer.step()
|
||||
|
||||
textual_inversion.write_loss(log_directory, "hypernetwork_loss.csv", hypernetwork.step, len(ds), {
|
||||
"loss": f"{previous_mean_loss:.7f}",
|
||||
"learn_rate": scheduler.learn_rate
|
||||
})
|
||||
steps_done = hypernetwork.step + 1
|
||||
|
||||
if images_dir is not None and steps_done % create_image_every == 0:
|
||||
forced_filename = f'{hypernetwork_name}-{steps_done}'
|
||||
last_saved_image = os.path.join(images_dir, forced_filename)
|
||||
if torch.isnan(losses[hypernetwork.step % losses.shape[0]]):
|
||||
raise RuntimeError("Loss diverged.")
|
||||
|
||||
if len(previous_mean_losses) > 1:
|
||||
std = stdev(previous_mean_losses)
|
||||
else:
|
||||
std = 0
|
||||
dataset_loss_info = f"dataset loss:{mean(previous_mean_losses):.3f}" + u"\u00B1" + f"({std / (len(previous_mean_losses) ** 0.5):.3f})"
|
||||
pbar.set_description(dataset_loss_info)
|
||||
|
||||
optimizer.zero_grad()
|
||||
shared.sd_model.cond_stage_model.to(devices.device)
|
||||
shared.sd_model.first_stage_model.to(devices.device)
|
||||
if hypernetwork_dir is not None and steps_done % save_hypernetwork_every == 0:
|
||||
# Before saving, change name to match current checkpoint.
|
||||
hypernetwork.name = f'{hypernetwork_name}-{steps_done}'
|
||||
last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork.name}.pt')
|
||||
hypernetwork.save(last_saved_file)
|
||||
|
||||
p = processing.StableDiffusionProcessingTxt2Img(
|
||||
sd_model=shared.sd_model,
|
||||
do_not_save_grid=True,
|
||||
do_not_save_samples=True,
|
||||
)
|
||||
textual_inversion.write_loss(log_directory, "hypernetwork_loss.csv", hypernetwork.step, len(ds), {
|
||||
"loss": f"{previous_mean_loss:.7f}",
|
||||
"learn_rate": scheduler.learn_rate
|
||||
})
|
||||
|
||||
if preview_from_txt2img:
|
||||
p.prompt = preview_prompt
|
||||
p.negative_prompt = preview_negative_prompt
|
||||
p.steps = preview_steps
|
||||
p.sampler_index = preview_sampler_index
|
||||
p.cfg_scale = preview_cfg_scale
|
||||
p.seed = preview_seed
|
||||
p.width = preview_width
|
||||
p.height = preview_height
|
||||
else:
|
||||
p.prompt = entries[0].cond_text
|
||||
p.steps = 20
|
||||
if images_dir is not None and steps_done % create_image_every == 0:
|
||||
forced_filename = f'{hypernetwork_name}-{steps_done}'
|
||||
last_saved_image = os.path.join(images_dir, forced_filename)
|
||||
|
||||
preview_text = p.prompt
|
||||
optimizer.zero_grad()
|
||||
shared.sd_model.cond_stage_model.to(devices.device)
|
||||
shared.sd_model.first_stage_model.to(devices.device)
|
||||
|
||||
processed = processing.process_images(p)
|
||||
image = processed.images[0] if len(processed.images)>0 else None
|
||||
p = processing.StableDiffusionProcessingTxt2Img(
|
||||
sd_model=shared.sd_model,
|
||||
do_not_save_grid=True,
|
||||
do_not_save_samples=True,
|
||||
)
|
||||
|
||||
if unload:
|
||||
shared.sd_model.cond_stage_model.to(devices.cpu)
|
||||
shared.sd_model.first_stage_model.to(devices.cpu)
|
||||
if preview_from_txt2img:
|
||||
p.prompt = preview_prompt
|
||||
p.negative_prompt = preview_negative_prompt
|
||||
p.steps = preview_steps
|
||||
p.sampler_index = preview_sampler_index
|
||||
p.cfg_scale = preview_cfg_scale
|
||||
p.seed = preview_seed
|
||||
p.width = preview_width
|
||||
p.height = preview_height
|
||||
else:
|
||||
p.prompt = entries[0].cond_text
|
||||
p.steps = 20
|
||||
|
||||
if image is not None:
|
||||
shared.state.current_image = image
|
||||
last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename, save_to_dirs=False)
|
||||
last_saved_image += f", prompt: {preview_text}"
|
||||
preview_text = p.prompt
|
||||
|
||||
shared.state.job_no = hypernetwork.step
|
||||
processed = processing.process_images(p)
|
||||
image = processed.images[0] if len(processed.images)>0 else None
|
||||
|
||||
shared.state.textinfo = f"""
|
||||
if unload:
|
||||
shared.sd_model.cond_stage_model.to(devices.cpu)
|
||||
shared.sd_model.first_stage_model.to(devices.cpu)
|
||||
|
||||
if image is not None:
|
||||
shared.state.current_image = image
|
||||
last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename, save_to_dirs=False)
|
||||
last_saved_image += f", prompt: {preview_text}"
|
||||
|
||||
shared.state.job_no = hypernetwork.step
|
||||
|
||||
shared.state.textinfo = f"""
|
||||
<p>
|
||||
Loss: {previous_mean_loss:.7f}<br/>
|
||||
Step: {hypernetwork.step}<br/>
|
||||
@ -512,14 +510,7 @@ Last saved hypernetwork: {html.escape(last_saved_file)}<br/>
|
||||
Last saved image: {html.escape(last_saved_image)}<br/>
|
||||
</p>
|
||||
"""
|
||||
finally:
|
||||
if weights:
|
||||
for weight in weights:
|
||||
weight.requires_grad = False
|
||||
if unload:
|
||||
shared.sd_model.cond_stage_model.to(devices.device)
|
||||
shared.sd_model.first_stage_model.to(devices.device)
|
||||
|
||||
|
||||
report_statistics(loss_dict)
|
||||
checkpoint = sd_models.select_checkpoint()
|
||||
|
||||
|
||||
@ -283,113 +283,111 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc
|
||||
embedding_yet_to_be_embedded = False
|
||||
|
||||
pbar = tqdm.tqdm(enumerate(ds), total=steps-ititial_step)
|
||||
for i, entries in pbar:
|
||||
embedding.step = i + ititial_step
|
||||
|
||||
try:
|
||||
for i, entries in pbar:
|
||||
embedding.step = i + ititial_step
|
||||
scheduler.apply(optimizer, embedding.step)
|
||||
if scheduler.finished:
|
||||
break
|
||||
|
||||
scheduler.apply(optimizer, embedding.step)
|
||||
if scheduler.finished:
|
||||
break
|
||||
if shared.state.interrupted:
|
||||
break
|
||||
|
||||
if shared.state.interrupted:
|
||||
break
|
||||
with torch.autocast("cuda"):
|
||||
c = cond_model([entry.cond_text for entry in entries])
|
||||
x = torch.stack([entry.latent for entry in entries]).to(devices.device)
|
||||
loss = shared.sd_model(x, c)[0]
|
||||
del x
|
||||
|
||||
with torch.autocast("cuda"):
|
||||
c = cond_model([entry.cond_text for entry in entries])
|
||||
x = torch.stack([entry.latent for entry in entries]).to(devices.device)
|
||||
loss = shared.sd_model(x, c)[0]
|
||||
del x
|
||||
losses[embedding.step % losses.shape[0]] = loss.item()
|
||||
|
||||
losses[embedding.step % losses.shape[0]] = loss.item()
|
||||
optimizer.zero_grad()
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
|
||||
optimizer.zero_grad()
|
||||
loss.backward()
|
||||
optimizer.step()
|
||||
steps_done = embedding.step + 1
|
||||
|
||||
steps_done = embedding.step + 1
|
||||
epoch_num = embedding.step // len(ds)
|
||||
epoch_step = embedding.step % len(ds)
|
||||
|
||||
epoch_num = embedding.step // len(ds)
|
||||
epoch_step = embedding.step % len(ds)
|
||||
pbar.set_description(f"[Epoch {epoch_num}: {epoch_step+1}/{len(ds)}]loss: {losses.mean():.7f}")
|
||||
|
||||
pbar.set_description(f"[Epoch {epoch_num}: {epoch_step+1}/{len(ds)}]loss: {losses.mean():.7f}")
|
||||
if embedding_dir is not None and steps_done % save_embedding_every == 0:
|
||||
# Before saving, change name to match current checkpoint.
|
||||
embedding.name = f'{embedding_name}-{steps_done}'
|
||||
last_saved_file = os.path.join(embedding_dir, f'{embedding.name}.pt')
|
||||
embedding.save(last_saved_file)
|
||||
embedding_yet_to_be_embedded = True
|
||||
|
||||
if embedding_dir is not None and steps_done % save_embedding_every == 0:
|
||||
# Before saving, change name to match current checkpoint.
|
||||
embedding.name = f'{embedding_name}-{steps_done}'
|
||||
last_saved_file = os.path.join(embedding_dir, f'{embedding.name}.pt')
|
||||
embedding.save(last_saved_file)
|
||||
embedding_yet_to_be_embedded = True
|
||||
write_loss(log_directory, "textual_inversion_loss.csv", embedding.step, len(ds), {
|
||||
"loss": f"{losses.mean():.7f}",
|
||||
"learn_rate": scheduler.learn_rate
|
||||
})
|
||||
|
||||
write_loss(log_directory, "textual_inversion_loss.csv", embedding.step, len(ds), {
|
||||
"loss": f"{losses.mean():.7f}",
|
||||
"learn_rate": scheduler.learn_rate
|
||||
})
|
||||
if images_dir is not None and steps_done % create_image_every == 0:
|
||||
forced_filename = f'{embedding_name}-{steps_done}'
|
||||
last_saved_image = os.path.join(images_dir, forced_filename)
|
||||
p = processing.StableDiffusionProcessingTxt2Img(
|
||||
sd_model=shared.sd_model,
|
||||
do_not_save_grid=True,
|
||||
do_not_save_samples=True,
|
||||
do_not_reload_embeddings=True,
|
||||
)
|
||||
|
||||
if images_dir is not None and steps_done % create_image_every == 0:
|
||||
forced_filename = f'{embedding_name}-{steps_done}'
|
||||
last_saved_image = os.path.join(images_dir, forced_filename)
|
||||
p = processing.StableDiffusionProcessingTxt2Img(
|
||||
sd_model=shared.sd_model,
|
||||
do_not_save_grid=True,
|
||||
do_not_save_samples=True,
|
||||
do_not_reload_embeddings=True,
|
||||
)
|
||||
if preview_from_txt2img:
|
||||
p.prompt = preview_prompt
|
||||
p.negative_prompt = preview_negative_prompt
|
||||
p.steps = preview_steps
|
||||
p.sampler_index = preview_sampler_index
|
||||
p.cfg_scale = preview_cfg_scale
|
||||
p.seed = preview_seed
|
||||
p.width = preview_width
|
||||
p.height = preview_height
|
||||
else:
|
||||
p.prompt = entries[0].cond_text
|
||||
p.steps = 20
|
||||
p.width = training_width
|
||||
p.height = training_height
|
||||
|
||||
if preview_from_txt2img:
|
||||
p.prompt = preview_prompt
|
||||
p.negative_prompt = preview_negative_prompt
|
||||
p.steps = preview_steps
|
||||
p.sampler_index = preview_sampler_index
|
||||
p.cfg_scale = preview_cfg_scale
|
||||
p.seed = preview_seed
|
||||
p.width = preview_width
|
||||
p.height = preview_height
|
||||
else:
|
||||
p.prompt = entries[0].cond_text
|
||||
p.steps = 20
|
||||
p.width = training_width
|
||||
p.height = training_height
|
||||
preview_text = p.prompt
|
||||
|
||||
preview_text = p.prompt
|
||||
processed = processing.process_images(p)
|
||||
image = processed.images[0]
|
||||
|
||||
processed = processing.process_images(p)
|
||||
image = processed.images[0]
|
||||
shared.state.current_image = image
|
||||
|
||||
shared.state.current_image = image
|
||||
if save_image_with_stored_embedding and os.path.exists(last_saved_file) and embedding_yet_to_be_embedded:
|
||||
|
||||
if save_image_with_stored_embedding and os.path.exists(last_saved_file) and embedding_yet_to_be_embedded:
|
||||
last_saved_image_chunks = os.path.join(images_embeds_dir, f'{embedding_name}-{steps_done}.png')
|
||||
|
||||
last_saved_image_chunks = os.path.join(images_embeds_dir, f'{embedding_name}-{steps_done}.png')
|
||||
info = PngImagePlugin.PngInfo()
|
||||
data = torch.load(last_saved_file)
|
||||
info.add_text("sd-ti-embedding", embedding_to_b64(data))
|
||||
|
||||
info = PngImagePlugin.PngInfo()
|
||||
data = torch.load(last_saved_file)
|
||||
info.add_text("sd-ti-embedding", embedding_to_b64(data))
|
||||
title = "<{}>".format(data.get('name', '???'))
|
||||
|
||||
title = "<{}>".format(data.get('name', '???'))
|
||||
try:
|
||||
vectorSize = list(data['string_to_param'].values())[0].shape[0]
|
||||
except Exception as e:
|
||||
vectorSize = '?'
|
||||
|
||||
try:
|
||||
vectorSize = list(data['string_to_param'].values())[0].shape[0]
|
||||
except Exception as e:
|
||||
vectorSize = '?'
|
||||
checkpoint = sd_models.select_checkpoint()
|
||||
footer_left = checkpoint.model_name
|
||||
footer_mid = '[{}]'.format(checkpoint.hash)
|
||||
footer_right = '{}v {}s'.format(vectorSize, steps_done)
|
||||
|
||||
checkpoint = sd_models.select_checkpoint()
|
||||
footer_left = checkpoint.model_name
|
||||
footer_mid = '[{}]'.format(checkpoint.hash)
|
||||
footer_right = '{}v {}s'.format(vectorSize, steps_done)
|
||||
captioned_image = caption_image_overlay(image, title, footer_left, footer_mid, footer_right)
|
||||
captioned_image = insert_image_data_embed(captioned_image, data)
|
||||
|
||||
captioned_image = caption_image_overlay(image, title, footer_left, footer_mid, footer_right)
|
||||
captioned_image = insert_image_data_embed(captioned_image, data)
|
||||
captioned_image.save(last_saved_image_chunks, "PNG", pnginfo=info)
|
||||
embedding_yet_to_be_embedded = False
|
||||
|
||||
captioned_image.save(last_saved_image_chunks, "PNG", pnginfo=info)
|
||||
embedding_yet_to_be_embedded = False
|
||||
last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename, save_to_dirs=False)
|
||||
last_saved_image += f", prompt: {preview_text}"
|
||||
|
||||
last_saved_image, last_text_info = images.save_image(image, images_dir, "", p.seed, p.prompt, shared.opts.samples_format, processed.infotexts[0], p=p, forced_filename=forced_filename, save_to_dirs=False)
|
||||
last_saved_image += f", prompt: {preview_text}"
|
||||
shared.state.job_no = embedding.step
|
||||
|
||||
shared.state.job_no = embedding.step
|
||||
|
||||
shared.state.textinfo = f"""
|
||||
shared.state.textinfo = f"""
|
||||
<p>
|
||||
Loss: {losses.mean():.7f}<br/>
|
||||
Step: {embedding.step}<br/>
|
||||
@ -398,9 +396,6 @@ Last saved embedding: {html.escape(last_saved_file)}<br/>
|
||||
Last saved image: {html.escape(last_saved_image)}<br/>
|
||||
</p>
|
||||
"""
|
||||
finally:
|
||||
if embedding and embedding.vec is not None:
|
||||
embedding.vec.requires_grad = False
|
||||
|
||||
checkpoint = sd_models.select_checkpoint()
|
||||
|
||||
|
||||
Loading…
Reference in New Issue
Block a user