diffusers
diffusers copied to clipboard
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
### Describe the bug `ImportError: cannot import name 'StableDiffusionSafetyChecker' from 'diffusers.pipelines.stable_diffusion' (/home/tiger/anaconda3/lib/python3.9/site-packages/diffusers/pipelines/stable_diffusion/__init__.py)` ### Reproduction _No response_ ### Logs _No response_ ### System Info diffusers=0.9.0 python=3.9
### Describe the bug ValueError: Unable to create tensor, you should probably activate truncation and/or padding with 'padding=True' 'truncation=True' to have batched tensors with the same length. Perhaps your features...
**What API design would you like to have changed or added to the library? Why?** I think the prediction type is a property of the unet since it describes what...
### Describe the bug I'm trying to use diffusers alongside another package, CLIP Interrogator. When I install the dependencies for CLIP Interrogator my diffuser code goes kerplooie! and throws this...
#1308 I've implemented the single-step high-order solvers in an elegant way. It is very similar to the implementations with the multi-step schedulers, and we do not need to modify pipelines....
This is required to improve the demo(s), we currently have the sliders disabled. Some users are also requesting it in discord and the forums. Our demo notebook is very fast...
## Idea I've been playing with this concept of mixed embeddings. The premise is simple: the pipeline takes a list of prompts and generates images based on a mix of...
### Describe the bug # FROM COLAB - version https://github.com/huggingface/diffusers/tree/main/examples/community#clip-guided-stable-diffusion Example | Description | Code Example | Colab | Author -- | -- | -- | -- | -- CLIP...
Context: https://twitter.com/jayelmnop/status/1585695941788856320 **Is your feature request related to a problem? Please describe.** The problem is that we don't have this awesome little pipeline! **Describe the solution you'd like** We add...
### Describe the bug Hi have been using diffusers, it works fine. after 10-20 model loading using `from_pretrained("CompVis/stable-diffusion-v1-4"` `from_pretrained("hakurei/waifu-diffusion"` . and tens of more, what i found is saved model...