https://github.com/nannullna/safeguard-hfi

Official implementation of "Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion" (ECCV 2024)
https://github.com/nannullna/safeguard-hfi

Last synced: 2 months ago
JSON representation

Official implementation of "Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion" (ECCV 2024)

• Host: GitHub
• URL: https://github.com/nannullna/safeguard-hfi
• Owner: nannullna
• License: mit
• Created: 2024-07-15T00:41:59.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-08-17T02:00:06.000Z (5 months ago)
• Last Synced: 2024-08-17T03:18:41.394Z (5 months ago)
• Homepage: https://nannullna.github.io/safeguard-hfi/
• Size: 628 KB
• Stars: 7
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-diffusion-categorized - [Code

README

        
# Safeguard with Human Feedback Inversion

Official implementation of "Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion" (ECCV 2024)

## WIP 🚧

We are currently finalizing the human annotation data and UI. The code and data will be available before the conference. 

* See [https://github.com/nannullna/safe-diffusion](https://github.com/nannullna/safe-diffusion) for Safe self-Distillation Diffusion (SDD). 

* See [https://huggingface.co/docs/diffusers/training/text_inversion](https://huggingface.co/docs/diffusers/training/text_inversion) and [https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion.py](https://github.com/huggingface/diffusers/blob/main/examples/textual_inversion/textual_inversion.py) for Textual Inversion.