diffusers icon indicating copy to clipboard operation
diffusers copied to clipboard

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Results 1193 diffusers issues
Sort by recently updated
recently updated
newest added

**Is your feature request related to a problem? Please describe.** Currently there is no way to create seamless textures with Stable Diffusion, a crucial feature that is missing. **Describe the...

community-examples
contributions-welcome

**What API design would you like to have changed or added to the library? Why?** Currently there's an inconsistency with image handling around depth maps. While you can provide either...

stale

I trained a model with diffusers. But I found the testing performance is not stable for the trained model. Sometimes, it can generate high-quality images, but sometimes, the images does...

stale

Hi @thedarkzeno and @patil-suraj Thanks for your excellent work on dream booth inpainting. My question is that how to perform fp16 dreambooth inpainting fine-tuning?

stale

### Describe the bug I'm preparing pipeline for upscale this way: ``` pipe = StableDiffusionUpscalePipeline.from_pretrained("stabilityai/stable-diffusion-2-1", use_auth_token="12345_token_4321", local_files_only=False, revision='fp16', torch_dtype=torch.float16, custom_pipeline="tiled_upscaling", low_cpu_mem_usage=True, low_res_scheduler=PNDMScheduler, ) ``` This always leads to error: ```...

bug
stale

### Describe the bug Hi, I'm in colab pro environment using TPU v2 for the test purpose. I get this error ```OSError: CompVis/stable-diffusion-v1-4 does not appear to have a file...

bug

**Is your feature request related to a problem? Please describe.** Currently, the StableDiffusionImg2ImgPipeline cannot output latents the way that the base StableDiffusionPipeline can. I think this would be a very...

…passed ideally check_inputs should not throw an error if both prompt and prompt embeds are passed as they can be later concatenated. leaving that as is for now to ensure...

### Model/Pipeline/Scheduler description Copied from https://github.com/huggingface/diffusers/pull/1858: > UnCLIP / Karlo: https://huggingface.co/spaces/kakaobrain/karlo gives some very nice and precise results when doing image generation and can strongly outperform Stable Diffusion in some...