diff options
Diffstat (limited to 'modules')
| -rw-r--r-- | modules/hypernetworks/hypernetwork.py | 10 | ||||
| -rw-r--r-- | modules/sd_hijack.py | 4 | ||||
| -rw-r--r-- | modules/textual_inversion/textual_inversion.py | 17 | ||||
| -rw-r--r-- | modules/ui.py | 9 |
4 files changed, 24 insertions, 16 deletions
diff --git a/modules/hypernetworks/hypernetwork.py b/modules/hypernetworks/hypernetwork.py index a2b3bc0a..4905710e 100644 --- a/modules/hypernetworks/hypernetwork.py +++ b/modules/hypernetworks/hypernetwork.py @@ -272,15 +272,17 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log optimizer.zero_grad()
loss.backward()
optimizer.step()
-
- pbar.set_description(f"loss: {losses.mean():.7f}")
+ mean_loss = losses.mean()
+ if torch.isnan(mean_loss):
+ raise RuntimeError("Loss diverged.")
+ pbar.set_description(f"loss: {mean_loss:.7f}")
if hypernetwork.step > 0 and hypernetwork_dir is not None and hypernetwork.step % save_hypernetwork_every == 0:
last_saved_file = os.path.join(hypernetwork_dir, f'{hypernetwork_name}-{hypernetwork.step}.pt')
hypernetwork.save(last_saved_file)
textual_inversion.write_loss(log_directory, "hypernetwork_loss.csv", hypernetwork.step, len(ds), {
- "loss": f"{losses.mean():.7f}",
+ "loss": f"{mean_loss:.7f}",
"learn_rate": scheduler.learn_rate
})
@@ -328,7 +330,7 @@ def train_hypernetwork(hypernetwork_name, learn_rate, batch_size, data_root, log shared.state.textinfo = f"""
<p>
-Loss: {losses.mean():.7f}<br/>
+Loss: {mean_loss:.7f}<br/>
Step: {hypernetwork.step}<br/>
Last prompt: {html.escape(entries[0].cond_text)}<br/>
Last saved embedding: {html.escape(last_saved_file)}<br/>
diff --git a/modules/sd_hijack.py b/modules/sd_hijack.py index 192883b2..f62ca1e9 100644 --- a/modules/sd_hijack.py +++ b/modules/sd_hijack.py @@ -29,8 +29,8 @@ def apply_optimizations(): ldm.modules.diffusionmodules.model.nonlinearity = silu
- if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (
- 6, 0) <= torch.cuda.get_device_capability(shared.device) <= (8, 6)):
+
+ if cmd_opts.force_enable_xformers or (cmd_opts.xformers and shared.xformers_available and torch.version.cuda and (6, 0) <= torch.cuda.get_device_capability(shared.device) <= (9, 0)):
print("Applying xformers cross attention optimization.")
ldm.modules.attention.CrossAttention.forward = sd_hijack_optimizations.xformers_attention_forward
ldm.modules.diffusionmodules.model.AttnBlock.forward = sd_hijack_optimizations.xformers_attnblock_forward
diff --git a/modules/textual_inversion/textual_inversion.py b/modules/textual_inversion/textual_inversion.py index f59b47a9..d2a389c9 100644 --- a/modules/textual_inversion/textual_inversion.py +++ b/modules/textual_inversion/textual_inversion.py @@ -88,9 +88,9 @@ class EmbeddingDatabase: data = []
- if filename.upper().endswith('.PNG'):
+ if os.path.splitext(filename.upper())[-1] in ['.PNG', '.WEBP', '.JXL', '.AVIF']:
embed_image = Image.open(path)
- if 'sd-ti-embedding' in embed_image.text:
+ if hasattr(embed_image, 'text') and 'sd-ti-embedding' in embed_image.text:
data = embedding_from_b64(embed_image.text['sd-ti-embedding'])
name = data.get('name', name)
else:
@@ -242,6 +242,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc last_saved_file = "<none>"
last_saved_image = "<none>"
+ embedding_yet_to_be_embedded = False
ititial_step = embedding.step or 0
if ititial_step > steps:
@@ -283,6 +284,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc if embedding.step > 0 and embedding_dir is not None and embedding.step % save_embedding_every == 0:
last_saved_file = os.path.join(embedding_dir, f'{embedding_name}-{embedding.step}.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}",
@@ -320,7 +322,7 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc shared.state.current_image = image
- if save_image_with_stored_embedding and os.path.exists(last_saved_file):
+ 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}-{embedding.step}.png')
@@ -329,15 +331,22 @@ def train_embedding(embedding_name, learn_rate, batch_size, data_root, log_direc info.add_text("sd-ti-embedding", embedding_to_b64(data))
title = "<{}>".format(data.get('name', '???'))
+
+ 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 = '{}'.format(embedding.step)
+ footer_right = '{}v {}s'.format(vectorSize, embedding.step)
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
image.save(last_saved_image)
diff --git a/modules/ui.py b/modules/ui.py index 1f6fcdc9..13ba3142 100644 --- a/modules/ui.py +++ b/modules/ui.py @@ -158,10 +158,7 @@ def save_files(js_data, images, do_make_zip, index): writer.writerow(["prompt", "seed", "width", "height", "sampler", "cfgs", "steps", "filename", "negative_prompt"])
for image_index, filedata in enumerate(images, start_index):
- if filedata.startswith("data:image/png;base64,"):
- filedata = filedata[len("data:image/png;base64,"):]
-
- image = Image.open(io.BytesIO(base64.decodebytes(filedata.encode('utf-8'))))
+ image = image_from_url_text(filedata)
is_grid = image_index < p.index_of_first_image
i = 0 if is_grid else (image_index - p.index_of_first_image)
@@ -638,7 +635,7 @@ def create_ui(wrap_gradio_gpu_call): txt2img_preview = gr.Image(elem_id='txt2img_preview', visible=False)
txt2img_gallery = gr.Gallery(label='Output', show_label=False, elem_id='txt2img_gallery').style(grid=4)
- with gr.Group():
+ with gr.Column():
with gr.Row():
save = gr.Button('Save')
send_to_img2img = gr.Button('Send to img2img')
@@ -862,7 +859,7 @@ def create_ui(wrap_gradio_gpu_call): img2img_preview = gr.Image(elem_id='img2img_preview', visible=False)
img2img_gallery = gr.Gallery(label='Output', show_label=False, elem_id='img2img_gallery').style(grid=4)
- with gr.Group():
+ with gr.Column():
with gr.Row():
save = gr.Button('Save')
img2img_send_to_img2img = gr.Button('Send to img2img')
|