hoelee/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-08-08 13:19:54 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge branch 'master' into hn-activation

Browse Source
This commit is contained in:
AUTOMATIC1111
2022-11-04 09:02:15 +03:00
committed by GitHub
parent 80844ac861 2cf3d2ac15
commit 4918eb6ce4
70 changed files with 7041 additions and 1309 deletions
Download Patch File Download Diff File Expand all files Collapse all files

89
modules/hypernetworks/hypernetwork.py
View File

@@ -25,6 +25,7 @@ from statistics import stdev, mean
class HypernetworkModule(torch.nn.Module):
multiplier = 1.0
activation_dict = {
"linear": torch.nn.Identity,
"relu": torch.nn.ReLU,
"leakyrelu": torch.nn.LeakyReLU,
"elu": torch.nn.ELU,
@@ -220,13 +221,16 @@ def list_hypernetworks(path):
res = {}
for filename in glob.iglob(os.path.join(path, '**/*.pt'), recursive=True):
name = os.path.splitext(os.path.basename(filename))[0]
res[name] = filename
# Prevent a hypothetical "None.pt" from being listed.
if name != "None":
res[name] = filename
return res
def load_hypernetwork(filename):
path = shared.hypernetworks.get(filename, None)
if path is not None:
# Prevent any file named "None.pt" from being loaded.
if path is not None and filename != "None":
print(f"Loading hypernetwork {filename}")
try:
shared.loaded_hypernetwork = Hypernetwork()
@@ -343,7 +347,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
# images allows training previews to have infotext. Importing it at the top causes a circular import problem.
from modules import images
assert hypernetwork_name, 'hypernetwork not selected'
save_hypernetwork_every = save_hypernetwork_every or 0
create_image_every = create_image_every or 0
textual_inversion.validate_train_inputs(hypernetwork_name, learn_rate, batch_size, data_root, template_file, steps, save_hypernetwork_every, create_image_every, log_directory, name="hypernetwork")
path = shared.hypernetworks.get(hypernetwork_name, None)
shared.loaded_hypernetwork = Hypernetwork()
@@ -369,39 +375,44 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
else:
images_dir = None
hypernetwork = shared.loaded_hypernetwork
checkpoint = sd_models.select_checkpoint()
ititial_step = hypernetwork.step or 0
if ititial_step >= steps:
shared.state.textinfo = f"Model has already been trained beyond specified max steps"
return hypernetwork, filename
scheduler = LearnRateScheduler(learn_rate, steps, ititial_step)
# dataset loading may take a while, so input validations and early returns should be done before this
shared.state.textinfo = f"Preparing dataset from {html.escape(data_root)}..."
with torch.autocast("cuda"):
ds = modules.textual_inversion.dataset.PersonalizedBase(data_root=data_root, width=training_width, height=training_height, repeats=shared.opts.training_image_repeats_per_epoch, placeholder_token=hypernetwork_name, model=shared.sd_model, device=devices.device, template_file=template_file, include_cond=True, batch_size=batch_size)
if unload:
shared.sd_model.cond_stage_model.to(devices.cpu)
shared.sd_model.first_stage_model.to(devices.cpu)
hypernetwork = shared.loaded_hypernetwork
weights = hypernetwork.weights()
for weight in weights:
weight.requires_grad = True
size = len(ds.indexes)
loss_dict = defaultdict(lambda : deque(maxlen = 1024))
losses = torch.zeros((size,))
previous_mean_losses = [0]
previous_mean_loss = 0
print("Mean loss of {} elements".format(size))
last_saved_file = "<none>"
last_saved_image = "<none>"
forced_filename = "<none>"
ititial_step = hypernetwork.step or 0
if ititial_step > steps:
return hypernetwork, filename
scheduler = LearnRateScheduler(learn_rate, steps, ititial_step)
weights = hypernetwork.weights()
for weight in weights:
weight.requires_grad = True
# if optimizer == "AdamW": or else Adam / AdamW / SGD, etc...
optimizer = torch.optim.AdamW(weights, lr=scheduler.learn_rate)
steps_without_grad = 0
last_saved_file = "<none>"
last_saved_image = "<none>"
forced_filename = "<none>"
pbar = tqdm.tqdm(enumerate(ds), total=steps - ititial_step)
for i, entries in pbar:
hypernetwork.step = i + ititial_step
@@ -440,7 +451,9 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
optimizer.step()
if torch.isnan(losses[hypernetwork.step % losses.shape[0]]):
steps_done = hypernetwork.step + 1
if torch.isnan(losses[hypernetwork.step % losses.shape[0]]):
raise RuntimeError("Loss diverged.")
if len(previous_mean_losses) > 1:
@@ -450,19 +463,19 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
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)
if hypernetwork.step > 0 and hypernetwork_dir is not None and hypernetwork.step % save_hypernetwork_every == 0:
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}-{hypernetwork.step}'
last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork.name}.pt')
hypernetwork.save(last_saved_file)
hypernetwork_name_every = f'{hypernetwork_name}-{steps_done}'
last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name_every}.pt')
save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, last_saved_file)
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 hypernetwork.step > 0 and images_dir is not None and hypernetwork.step % create_image_every == 0:
forced_filename = f'{hypernetwork_name}-{hypernetwork.step}'
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)
optimizer.zero_grad()
@@ -499,7 +512,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log
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)
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
@@ -515,13 +528,23 @@ Last saved image: {html.escape(last_saved_image)}<br/>
"""
report_statistics(loss_dict)
checkpoint = sd_models.select_checkpoint()
hypernetwork.sd_checkpoint = checkpoint.hash
hypernetwork.sd_checkpoint_name = checkpoint.model_name
# Before saving for the last time, change name back to the base name (as opposed to the save_hypernetwork_every step-suffixed naming convention).
hypernetwork.name = hypernetwork_name
filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork.name}.pt')
hypernetwork.save(filename)
filename = os.path.join(shared.cmd_opts.hypernetwork_dir, f'{hypernetwork_name}.pt')
save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, filename)
return hypernetwork, filename
def save_hypernetwork(hypernetwork, checkpoint, hypernetwork_name, filename):
old_hypernetwork_name = hypernetwork.name
old_sd_checkpoint = hypernetwork.sd_checkpoint if hasattr(hypernetwork, "sd_checkpoint") else None
old_sd_checkpoint_name = hypernetwork.sd_checkpoint_name if hasattr(hypernetwork, "sd_checkpoint_name") else None
try:
hypernetwork.sd_checkpoint = checkpoint.hash
hypernetwork.sd_checkpoint_name = checkpoint.model_name
hypernetwork.name = hypernetwork_name
hypernetwork.save(filename)
except:
hypernetwork.sd_checkpoint = old_sd_checkpoint
hypernetwork.sd_checkpoint_name = old_sd_checkpoint_name
hypernetwork.name = old_hypernetwork_name
raise