huggingface / diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
https://huggingface.co/docs/diffusers
Apache License 2.0
26.24k stars 5.41k forks source link

BDIA-DDIM Scheduler #9957

Open Jdh235 opened 2 hours ago

Jdh235 commented 2 hours ago

Model/Pipeline/Scheduler description

The BDIA-DDIM scheduler was first applied in stable diffusion in the ECCV 2024 paper "Exact Diffusion Inversion via Bi-directional Integration Approximation" by Guoqiang Zhang, J. P. Lewis, and W. Bastiaan Kleijn. Below are results from the initial implementation for text-to-image generation using StableDiffusion V2.

The BDIA-DDIM Scheduler improves image sampling quality over traditional DDIM through a more accurate integral approximation, with negligible computational overhead. Experiments further show that BDIA-DDIM produces markedly better image sampling qualities than DDIM for text-to-image generation, thanks to the more accurate integration approximation. Since the first implementation, I have forked the diffusers library to integrate BDIA-DDIM as an additional scheduler and have found it produces significantly better results, especially at lower timesteps.

BDIADDIM_t2i_20pairs

Open source status

Provide useful links for the implementation

Original Paper: "Exact Diffusion Inversion via Bi-directional Integration Approximation" by Guoqiang Zhang, J. P. Lewis, and W. Bastiaan Kleijn.

Original Implementation: https://github.com/guoqiang-zhang-x/BDIA

My diffusers implementation: https://github.com/Jdh235/diffusers

a-r-r-o-w commented 2 hours ago

cc @yiyixuxu @asomoza