Skip to content

Conversation

@mwkldeveloper
Copy link
Contributor

What does this PR do?

Follow the advise #6241 (comment)
fix RuntimeError: Input type (float) and bias type (c10::Half) should be the same in train_text_to_image_lora.py

Fixes # (issue)
Apply autocast block to the caller of pipline in train_text_to_image_lora.py

@HuggingFaceDocBuilderDev

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

@sayakpaul sayakpaul merged commit 2d43094 into huggingface:main Dec 24, 2023
donhardman pushed a commit to donhardman/diffusers that referenced this pull request Dec 29, 2023
… be the same in train_text_to_image_lora.py (huggingface#6259)

* fix RuntimeError: Input type (float) and bias type (c10::Half) should be the same

* format source code

* format code

* remove the autocast blocks within the pipeline

* add autocast blocks to pipeline caller in train_text_to_image_lora.py
antoine-scenario pushed a commit to antoine-scenario/diffusers that referenced this pull request Jan 2, 2024
… be the same in train_text_to_image_lora.py (huggingface#6259)

* fix RuntimeError: Input type (float) and bias type (c10::Half) should be the same

* format source code

* format code

* remove the autocast blocks within the pipeline

* add autocast blocks to pipeline caller in train_text_to_image_lora.py
AmericanPresidentJimmyCarter pushed a commit to AmericanPresidentJimmyCarter/diffusers that referenced this pull request Apr 26, 2024
… be the same in train_text_to_image_lora.py (huggingface#6259)

* fix RuntimeError: Input type (float) and bias type (c10::Half) should be the same

* format source code

* format code

* remove the autocast blocks within the pipeline

* add autocast blocks to pipeline caller in train_text_to_image_lora.py
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants