diffusers
diffusers copied to clipboard
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
Problem: xformers being available doesn't always mean it should be used. For example, I install xformers because it makes inference fast but I find xformers make my dreambooth training slower....
### Context The #1526 PR implemented a `PipelineTesterMixin` with common fast tests for pipelines to inherit: saving/loading, casting to fp16, checking tuple outputs, attention slicing, etc. To support `PipelineTesterMixin`, a...
**Is your feature request related to a problem? Please describe.** I'm using the new Flax pipeline for dreambooth training and want to be able to use the trained model on...
### Describe the bug I'm following the examples/dreambooth README, and after installing dependencies, I cannot configurate accelerate. When I run `accelerate config` or `accelerate config default`, it gives the following...
As mentioned in the question, Does diffusers support Stable Diffusion Version 2 now? If supported,how to use it?Thanks.
Cloned the repo and tried using the convert_original_stable diffusion_to_diffusers.py to convert my .ckpt file and I'm getting a `sudo: ./scripts/convert_original_stable_diffusion_to_diffusers.py: command not found` error. Any idea what I can do...
### Describe the bug When running the pytest suite, almost all xformers tests are all failing due to assertion errors, ### Reproduction `pytest -k "xformers" tests ` ### Logs ```shell...
Hi, When we pass a prompt to the pip (from for eg: pipe = StableDiffusionPipeline.from_pretrained("./stable-diffusion-v1-5")), it displays an output in this case, with a progress bar. Is it possible to...
- Correctly update the progress bar every epoch - Allow specifying a pretrained VAE - Allow specifying a revision to pretrained models - Cache compiled models between invocations (speeds up...
Does anyone know a way to train dream booth with runway inpainting?