diffusers

diffusers copied to clipboard

Support training SD V2 with Flax

3

Mostly involves supporting a v_prediction scheduler. The implementation in #1777 doesn't take into account a recent refactor of `scheduling_utils_flax`, so this should be used instead.

yasyf

**Is your feature request related to a problem? Please describe.** When trying to call scheduler.step with multiple timesteps it throws an error: `Boolean value of Tensor with more than one...

bonlime

Unclip image variation

1

williamberman

fix small mistake in annotation: 32 -> 64

1

Fix inconsistencies between code and comments in the function 'preprocess'

Line290

I would like to contribute to translating the documentation into Korean. It seems that there is a version and language selection in the docs, but only EN is currently supported....

seriousran

Dynamic modules fail when using a cache shared across users

4

### Describe the bug If multiple users attempt to share the same models cache (e.g., on a company internal shared file system), custom pipelines fail to load. As encountered in...

antoche

[Community] Add dropout to Flax UNet

3

### Describe the bug Flax UNet currently doesn't support dropout ### Reproduction _No response_ ### Logs _No response_ ### System Info Main

patrickvonplaten

Unconditional Image Generation generating noise

1

Hi, As mentioned in https://huggingface.co/docs/diffusers/training/unconditional_training, I am trying to fine-tune on the CartoonSet[https://google.github.io/cartoonset/] dataset. However, after training for 100 epochs, on inspecting via Tensorboard, I still see only noise being...

agneet42

A6000 GPU: Getting torch.cuda.OutOfMemoryError: CUDA out of memory

1

I am trying to finetune a dreambooth model using diffusers repo. GPU: **A6000 48GB VRAM** but getting the following error: ``` torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1.50...

geekyayush

attention.py test can force you to uninstall xformer

3

### Describe the bug https://github.com/huggingface/diffusers/blob/9f8c915a756cf937a428186a2af8cc56f029f689/src/diffusers/models/attention.py#L305 https://github.com/huggingface/diffusers/blob/9f8c915a756cf937a428186a2af8cc56f029f689/src/diffusers/models/attention.py#L468 I have users that have xformer pre-compiled, but it not always work on their local computer. I do my own tests before calling set_use_memory_efficient_attention_xformers,...

BurguerJohn