Speed up image generation with improved image quality using Agent Attention.
- SD 1.5 Support
- SD XL Support (Requires Max Downsample > 1. If anybody knows the ideal settings to get this to work, please open an Issue!)
- The authors of the original paper for their method (https://arxiv.org/abs/2312.08874):
@misc{han2023agent, title={Agent Attention: On the Integration of Softmax and Linear Attention}, author={Dongchen Han and Tianzhu Ye and Yizeng Han and Zhuofan Xia and Shiji Song and Gao Huang}, year={2023}, eprint={2312.08874}, archivePrefix={arXiv}, primaryClass={cs.CV} }
- This extension uses code from the official AgentAttention repository: https://github.com/LeapLabTHU/Agent-Attention
- @udon-universe's extension templates (https://github.com/udon-universe/stable-diffusion-webui-extension-templates)