mihirp1998/AlignProp

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion

35
/ 100
Emerging

314 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

314

Forks

11

Language

Python

License

MIT

Category

diffusion-rlhf-alignment

Last pushed

Nov 01, 2024

Commits (30d)

0

GitHub
Diffusion RLHF Alignment · 53 models

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mihirp1998/AlignProp"

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

Higher-rated alternatives

FlorianFuerrutter/genQC

Generative Quantum Circuits

72

horseee/DeepCache

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

63

Gen-Verse/MMaDA

MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion,...

51

kuleshov-group/mdlm

[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model

49

Shark-NLP/DiffuSeq

[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models

47

Explore Diffusion Models

All categories Trending Diffusion directory Insights