Skip to content

fix RuntimeError: Input type (float) and bias type (c10::Half) should be the same in train_text_to_image_lora.py #6259

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
sayakpaul merged 7 commits into from
Dec 24, 2023
Merged

fix RuntimeError: Input type (float) and bias type (c10::Half) should be the same in train_text_to_image_lora.py #6259

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
1e075a1
fix RuntimeError: Input type (float) and bias type (c10::Half) should…
mwkldeveloper Dec 20, 2023
677b904
Merge branch 'huggingface:main' into main
mwkldeveloper Dec 20, 2023
24438a3
format source code
mwkldeveloper Dec 20, 2023
cef7d3a
format code
mwkldeveloper Dec 20, 2023
83be15a
Merge branch 'main' of https://github.com/mwkldeveloper/diffusers
mwkldeveloper Dec 21, 2023
f7b86c6
remove the autocast blocks within the pipeline
mwkldeveloper Dec 21, 2023
9abdbe1
add autocast blocks to pipeline caller in train_text_to_image_lora.py
mwkldeveloper Dec 21, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 10 additions & 6 deletions examples/text_to_image/train_text_to_image_lora.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -844,10 +844,11 @@ def collate_fn(examples):
if args.seed is not None:
generator = generator.manual_seed(args.seed)
images = []
for _ in range(args.num_validation_images):
images.append(
pipeline(args.validation_prompt, num_inference_steps=30, generator=generator).images[0]
)
with torch.cuda.amp.autocast():
for _ in range(args.num_validation_images):
images.append(
pipeline(args.validation_prompt, num_inference_steps=30, generator=generator).images[0]
)

for tracker in accelerator.trackers:
if tracker.name == "tensorboard":
Expand Down Expand Up @@ -913,8 +914,11 @@ def collate_fn(examples):
if args.seed is not None:
generator = generator.manual_seed(args.seed)
images = []
for _ in range(args.num_validation_images):
images.append(pipeline(args.validation_prompt, num_inference_steps=30, generator=generator).images[0])
with torch.cuda.amp.autocast():
for _ in range(args.num_validation_images):
images.append(
pipeline(args.validation_prompt, num_inference_steps=30, generator=generator).images[0]
)

for tracker in accelerator.trackers:
if len(images) != 0:
Expand Down