diffusers

diffusers copied to clipboard

[Core] add auto `device_map` support to pipelines

37

# What does this PR do? As per what's discussed in https://github.com/huggingface/diffusers/pull/6396, this PR adds support for "balanced" device map (and other variants) in the pipelines. It's NOT complete yet....

sayakpaul

[WIP ] Add AnimateDiff SparseCntrl

10

# What does this PR do? Add AnimateDiff SparseCntrl model to diffusers https://github.com/guoyww/AnimateDiff/tree/main?tab=readme-ov-file#202312-animatediff-v3-and-sparsectrl TODO: - [x] Convert checkpoints to diffusers format - [x] Add sparse control pipeline and sparse controlnet...

DN6

SDXL Fooocus Inpaint

50

**Is your feature request related to a problem? Please describe.** I have seen that diffusers StableDiffusionXLInpaintPipeline generates worse results than SD 1.5 pipeline. **Describe the solution you'd like.** Include Fooocus...

WaterKnight1998

[Chore] switch to `logger.warning`

1

# What does this PR do? To avoid continuous deprecation messages.

sayakpaul

[Dreambooth example run error] When I use the downloaded pretrained_model I still get network errors

7

Hello,it's a great work! I have downloaded the pre-trained model in advance. My question is why there are still network errors during the training process? My windows system environment is...

xdobetter

Update model card template train_text_to_image_lora_sdxl.py

8

# What does this PR do? Instead of saying "LoRA for the text encoder was enabled: (true/false)", say "LoRA for the text encoder was enabled" when true. ## Before submitting...

sr5434

Adding TextualInversionLoaderMixin for the controlnet_inpaint_sd_xl pipeline

8

# What does this PR do? The pipeline controlnet_inpaint_sd_xl pipeline contained the textual_inversion loading logic, but did not load the TextualInversionLoaderMixin yet. ## Who can review? Anyone in the community...

jschoormans

Add AudioLDM2 TTS

14

# What does this PR do? In #4549 @sanchit-gandhi has implemented AudioLDM2 but no TTS. In this PR I convert gigaspeech checkpoint and implement TTS pipeline for AudioLDM2 Fixes #...

tuanh123789

log loss per image

1

# What does this PR do? logging loss for each image in dataset. Given that Lora datasets are usually small this feature might help to one to spot low-quality images...

noskill

Fix loading Img2Img refiner components in `from_single_file`

1

# What does this PR do? `set_additional_components` for SDXL refiner based pipelines in `from_single_file` is breaking because no checkpoint argument is passed in. This PR 1. Passes in the checkpoint...

DN6