diffusers
diffusers copied to clipboard
huggingface
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Thanks for the opportunity to fix #6407! >AnyText comprises a diffusion pipeline with two primary elements: an auxiliary latent module and a text embedding module. The former uses inputs like...
# What does this PR do? Fixes #8710 Partially ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks...
# What does this PR do? ## Issue This addresses an issue discussed in a two PRs, see https://github.com/huggingface/diffusers/pull/9406#issuecomment-2359371560 and https://github.com/huggingface/diffusers/pull/9507#issuecomment-2375884213 The FLUX controlnet pipeline is actually lacking any checks...
# What does this PR do? Adds support for Pyramid Attention Broadcast. - Paper: https://www.arxiv.org/abs/2408.12588 - Project Page: https://oahzxl.github.io/PAB/ - Code: https://github.com/NUS-HPC-AI-Lab/VideoSys We only add the changes related to attention,...
### Describe the bug I believe the SNR weighting of v_prediction should follow a similar trend as eps, otherwise, for T>600, the model learns almost nothing as the weight approaches...
### Describe the bug CogVideoX I2V: There is a warning when the negative_prompt is defined, but no warning when num_frames is defined, however, the latter will cause a faulty render,...
# What does this PR do? Support [LinFusion](https://huggingface.co/papers/2409.02097). It accelerates diffusion models by replacing all the self-attention layers in a diffusion UNet with distilled Generalized Linear Attention layers. The distilled...
### Model/Pipeline/Scheduler description Authors of the paper trained a base controlnet (with a new architecture if I'm not mistaken) on 9 different conditions to allow finetuning on new conditions easily...
### Describe the bug The DPMSolverSinglestepScheduler throws a value error "step must be greater than zero" in terminal. No other scheduler had this issue. When I set clipped_idx to be...
Metadata
Owner
Metadata
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.