hu-zijing/D-Fusion

[ICML 25] Denoising trajectory fusion, a method to construct RL-trainable visually consistent samples.

29
/ 100
Experimental

This project helps researchers and practitioners fine-tune diffusion models to better understand what makes a generated image align with a text prompt. It takes a diffusion model and poorly-aligned image-text pairs, and outputs improved, visually consistent image samples that are suitable for further training. This is for machine learning researchers and AI developers working on improving text-to-image generation.

No commits in the last 6 months.

Use this if you are working on aligning diffusion models with text prompts and need to generate visually consistent samples for effective direct preference optimization (DPO) training.

Not ideal if you are a casual user looking to generate images or if you need a solution compatible with the absolute latest versions of diffusion model libraries without manual code adaptation.

Diffusion Models Reinforcement Learning Generative AI Image Generation Model Alignment
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Python

License

MIT

Last pushed

Jun 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hu-zijing/D-Fusion"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.