diffusers
diffusers copied to clipboard
huggingface
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
### Describe the bug I am trying to use a model hosted on huggingface and I have created an inference endpoint for it. I have attached the code I used...
### Describe the bug When generating multiple videos (say batch size = 2), SVD will give 1 correct generation and 1 incorrect one. ### Reproduction video = pipeline(..., num_videos_per_prompt=2, ...)...
# What does this PR do? Made some updates to the original PR: #5853 Doc pages that are not tested include - Training examples (these should be tested in with...
Related to https://github.com/huggingface/doc-builder/pull/487 and [internal slack thread](https://huggingface.slack.com/archives/C04F8N7FQNL/p1711384899462349?thread_ts=1711041424.720769&cid=C04F8N7FQNL). There is now a `custom_container` option when building docs in CI. When set to `""` (instead of `"huggingface/transformers-doc-builder"` by default), we don't run...
# What does this PR do? We have a bunch of attention processors, normalization layers, and activation layers in the codebase and they have thin documentation. This is fine because...
Code to reproduce: ```python from diffusers import LCMScheduler, StableDiffusionXLPipeline import torch pipeline = StableDiffusionXLPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-1.0", torch_dtype=torch.float16).to("cuda") pipeline.load_lora_weights("latent-consistency/lcm-lora-sdxl") pipeline.fuse_lora() pipeline.scheduler = LCMScheduler.from_config(pipeline.scheduler.config) _ = pipe( prompt="a dog", num_inference_steps=4, guidance_scale=1.0, ) ``` Unexpected...
https://github.com/huggingface/diffusers/blob/f4fc75035f2d567dfe00fc6b8671ecd38dd144b2/src/diffusers/schedulers/scheduling_dpmsolver_multistep_flax.py#L164 Apparently, `q` in [jnp.percentile](https://jax.readthedocs.io/en/latest/_autosummary/jax.numpy.percentile.html) should between [0, 100] instead of [0, 1] as in torch.
# What does this PR do? One potential cause for timeout issues in the Pipeline tests could be that the shared memory size for the container is set to 16GB....
# What does this PR do? Part of #7677 Before: ``` pytest -s tests/pipelines/animatediff/test_animatediff.py 213.80s user 10.60s system 182% cpu 2:02.86 total ``` After: ``` pytest -s tests/pipelines/animatediff/test_animatediff.py 40.48s user...
# What does this PR do? This PR is similar to https://github.com/huggingface/diffusers/pull/3462 but fixes the same issue in ```train_dreambooth.py```. Fixes https://github.com/huggingface/diffusers/issues/7619 ## Before submitting - [ ] This PR fixes...
Metadata
Owner
Metadata
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.