diffusers
diffusers copied to clipboard
huggingface
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
Body: ### Describe the bug When importing `diffusers` on a non-CUDA system (e.g., Apple Silicon Mac with MPS), a warning is emitted: /torch/amp/autocast_mode.py:270: UserWarning: User provided device_type of 'cuda', but...
# What does this PR do? When memory is constrained, VAE tiling serves as a critical optimization to reduce memory footprint—here’s how it works at its core: 1. Split the...
# What does this PR do? This PR now modifies the ContextParallelSplitHook and ContextParallelGatherHook to gracefully handle sequence lengths that are not divisible by the world size. This PR changes:...
# What does this PR do? Fixes https://github.com/huggingface/diffusers/issues/12600 Functionality-wise the self attention cache seems to work correctly, cross-attention has to be added and verfied. I added Krea to test the...
Fixes #12755. This PR documents the expected shape of the `latents` argument in `Flux2Pipeline.__call__`. For the default `AutoencoderKLFlux2` VAE used by FLUX.2, the pipeline first applies 8× spatial compression in...
The shape of the `latent` argument is not, as users might guess, `(1, 16, h//8, w//8)`, but `(1, 128, h//16, w//16)`. This should be documented.
# What does this PR do? Enables robust batch inference for `QwenImageEditPlusPipeline` by normalizing input tensor shapes, implementing a "resize" strategy, and handling variable-length prompt embeddings. Adds a new batch...
# What does this PR do? This is weird: https://github.com/huggingface/diffusers/actions/runs/20024136669/job/57417539471#step:7:275 This PR ensures that after the `diffusers` installations, we always are on a stable `transformers` release. Also changed to Python...
### Describe the bug I am trying to run the batch inference for 'Qwen-Image-Edit-2509', but it will raise inference error ``` AttributeError Traceback (most recent call last) .venv/lib/python3.10/site-packages/diffusers/pipelines/qwenimage/pipeline_qwenimage_edit_plus.py:633) height =...
# What does this PR do? As the title suggests, this PR adds a test suite for the custom blocks in modular diffusers. * `TestModularCustomBlocks` tests for basic checks, e.g.,...
Metadata
Owner
Metadata
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.