diffusers
diffusers copied to clipboard
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
I want to fine-tune IP-adapter model with xformers, but I did not find the implementation of the xformers version corresponding to IPAdapterAttnProcessor2_0. I want to implement attention processor in xformers,...
# What does this PR do? Fixes PixArt Sigma tests. Cc: @lawrence-cj for awareness.
### Describe the bug When using enable_model_cpu_offload on StableDiffusionXLPipeline, each consecutive __call__ takes more and more RAM. Also, after deleting pipe not all memory is freed ### Reproduction ```python import...
# What does this PR do? Apologies for not giving enough consideration to it before. So, with the help of @glegendre01, we devised a more secure way to achieve what...
Add `cross_attention_kwargs` to `__call__` method of `StableDiffusionInstructPix2PixPipeline`, which are passed to UNet. # What does this PR do? Implements https://github.com/huggingface/diffusers/issues/7962 Adding ability to pass custom cross-attention arguments for UNet. This...
# What does this PR do? This PR adds a discrete and continuous time scheduler based on the [Variational Diffusion Models](https://arxiv.org/abs/2107.00630) (VDM) formulation, i.e. expressing the diffusion process via the...
### Describe the bug As far as I know, UNetMotionModel is adopted for AnimateDiff. Hence, I look into the original implementation of AnimateDiff, it is noticed that they use cross-attention...
Investigates why the `VideoProcessor` doc fails to build. I think it may have to do with how the `video` parameter is formatted in the docstring (related to #7937).
This PR adapts @asomoza's outpaint [blog post 3](https://huggingface.co/blog/OzzyGT/outpainting-inpaint-model) for the docs.
# What does this PR do? Supports custom sigmas and timesteps for SDXL ControlNet Inpainting and SDXL ControlNet Img2Img pipelines ## Before submitting - [ ] This PR fixes a...