diffusers
diffusers copied to clipboard
huggingface
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
# What does this PR do? Since the release of Playground V2.5 with "custom" VAE we should normalize and denormalize latents. This is already implemented in `StableDiffusionXLPipeline`: https://github.com/huggingface/diffusers/blob/687bc2772721af584d649129f8d2a28ca56a9ad8/src/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl.py#L1230-L1243 ## Who...
# What does this PR do? This PR adds a pipeline and scheduler for the [UFOGen model](https://arxiv.org/pdf/2311.09257.pdf). The UFOGen model is based on the [denoising diffusion GAN (DDGAN) model](https://arxiv.org/pdf/2112.07804.pdf) with...
### Describe the bug I am unable to resume training of a locally saved SD 1.5 model (trained using the same text-image.py script, albeit likely an earlier revision). There is...
Bug fix for controlnetpipeline check_image when using multicontrolnet and prompt list Fixes # (issue) [https://github.com/huggingface/diffusers/issues/7102](https://github.com/huggingface/diffusers/issues/7102) @sayakpaul
### Model/Pipeline/Scheduler description Novel-view synthesis through diffusion models has demonstrated remarkable potential for generating diverse and high-quality images. Yet, the independent process of image generation in these prevailing methods leads...
stabilityai/stable-diffusion-2-base DDIM config is not compatible with current DDIM implementation
### Describe the bug Assume 30 inference steps. There are two 925, and the number of inference steps is 31. tensor([958, 925, 925, 892, 859, 826, 793, 760, 727, 694,...
### Describe the bug The model KohakuXL in diffusers, seems to run into a massive noise/stability issue that doesn't seem to be present within ComfyUI/AUTO1111, on UniPC/DPM schedulers (possibly more)...
### Model/Pipeline/Scheduler description The generative priors of pre-trained latent diffusion models have demonstrated great potential to enhance the perceptual quality of image super-resolution (SR) results. Unfortunately, the existing diffusion prior-based...
outpainting is very interesting does diffusers support it?
SDXL for Outpainting functionality can be improved. Attached are some attempts at Outpainting with `StableDiffusionXLInpaintPipeline` and `stabilityai/stable-diffusion-xl-base-1.0` checkpoint. Given this image/mask combination ((black pixels ignored and white pixels are to...
Metadata
Owner
Metadata
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.