diffusers

diffusers copied to clipboard

[community] Improving docstrings and type hints

15

There are many instances in the codebase where our docstring/typing convention is not followed. We'd like to work on improving this with your help! Our convention looks like: ```python3 def...

a-r-r-o-w

With examples/dreambooth /README_flux.md guide setting up and training, got cuda OOM with 3090Ti 24GB

1

### Describe the bug Followed the guide examples/dreambooth/README_flux.md guide setting up and training, got cuda OOM with 3090Ti 24GB. ### Reproduction PC got 256GB RAM 3090Ti VRAM 24GB torch 2.4.1...

riflemanl

### Describe the bug Hi, I have been working on training models using the same dataset as "stabilityai/stable-diffusion-xl-base-1.0" with the script examples/text_to_image/train_text_to_image_lora_sdxl.py, and I achieved quite promising results. Now, I...

hjw-0909

The Modular Diffusers

40

# Notes * overrided this PR https://github.com/huggingface/diffusers/pull/11652/files, need to make sure new code works for this case # Getting Started with Modular Diffusers With Modular Diffusers, we introduce a unified...

yiyixuxu

Flux-dev docker image error

4

### Describe the bug ``` PS F:\cog-flux-dev> docker images REPOSITORY TAG IMAGE ID CREATED SIZE flux-dev-model latest c19d0ffc3660 11 minutes ago 55.1GB ``` After build docker image..i have run that...

tzktok

### Discussed in https://github.com/huggingface/diffusers/discussions/9710 Originally posted by **LianShuaiLong** October 18, 2024 To save GPU memory during training, I pre-extracted the text embeddings. During the training process, I did not load...

LianShuaiLong

[docs] refactoring docstrings in ./src/diffusers/models/transformers/auraflow_transformer_2d.py

1

# What does this PR do? Fixes https://github.com/huggingface/diffusers/issues/9567 (I reopened PR with same doc since my previous PR may occur sync issue. sorry for confusion!) Fixes # (issue) - Unified...

ahnjj

consistency in argument names

1

### Describe the bug `tokens` should be `token` for consistency with load method: https://huggingface.co/docs/diffusers/en/api/loaders/textual_inversion#diffusers.loaders.TextualInversionLoaderMixin.unload_textual_inversion Load method https://huggingface.co/docs/diffusers/en/api/loaders/textual_inversion#diffusers.loaders.TextualInversionLoaderMixin.load_textual_inversion uses single argument `token=` ### Reproduction - ### Logs _No response_ ### System...

christopher5106

why rebuild a vae in inference stage?

1

Thanks for ur effort for diffusion model. I want to know why we need to rebuild a vae in inference stage. I think it will introduce extra GPU cost. https://github.com/huggingface/diffusers/blob/a85b34e7fdc0a5fceb11aa0fa6199bd9afaca396/examples/text_to_image/train_text_to_image_sdxl.py#L1217C16-L1223C24

WilliammmZ

Can we allow making everything on gpu/cuda for scheduler?

12

**What API design would you like to have changed or added to the library? Why?** Is it possible to allow setting every tensor attribute of scheduler to cuda device? In...

xiang9156