https://github.com/RockeyCoss/SPO

Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step
https://github.com/RockeyCoss/SPO

diffusion-models dpo sdxl text-to-image text-to-image-generation

Last synced: about 2 months ago
JSON representation

Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step

• Host: GitHub
• URL: https://github.com/RockeyCoss/SPO
• Owner: RockeyCoss
• Created: 2024-05-26T22:31:44.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-07-10T05:12:54.000Z (3 months ago)
• Last Synced: 2024-07-10T07:19:19.549Z (3 months ago)
• Topics: diffusion-models, dpo, sdxl, text-to-image, text-to-image-generation
• Language: Python
• Homepage: https://arxiv.org/abs/2406.04314
• Size: 30.5 MB
• Stars: 99
• Watchers: 4
• Forks: 2
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-diffusion-categorized - [Code