Diffusion RLHF Alignment Diffusion Models

Tools and methods for aligning diffusion models using reinforcement learning and human feedback, including preference optimization, reward modeling, and RLHF fine-tuning techniques. Does NOT include general diffusion model training, inference optimization, or non-RL-based fine-tuning methods like LoRA.

There are 57 diffusion rlhf alignment models tracked. 3 score above 50 (established tier). The highest-rated is FlorianFuerrutter/genQC at 61/100 with 57 stars.

Get all 57 projects as JSON

curl "https://pt-edge.onrender.com/api/v1/datasets/quality?domain=diffusion&subcategory=diffusion-rlhf-alignment&limit=20"

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

#	Model	Score	Tier	Stars	Language
1	FlorianFuerrutter/genQC Generative Quantum Circuits	61	Established	57	Jupyter Notebook
2	horseee/DeepCache [CVPR 2024] DeepCache: Accelerating Diffusion Models for Free	53	Established	963	Python
3	Gen-Verse/MMaDA MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with...	51	Established	1,611	Python
4	kuleshov-group/mdlm [NeurIPS 2024] Simple and Effective Masked Diffusion Language Model	49	Emerging	657	Python
5	Shark-NLP/DiffuSeq [ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models	47	Emerging	831	Python
6	jeongwhanchoi/SCONE "SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard...	43	Emerging	15	Python
7	ali-vilab/TeaCache Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model	42	Emerging	1,290	Python
8	Hzfinfdu/Diffusion-BERT ACL'2023: DiffusionBERT: Improving Generative Masked Language Models with...	40	Emerging	339	Python
9	Xiuyu-Li/q-diffusion [ICCV 2023] Q-Diffusion: Quantizing Diffusion Models.	40	Emerging	371	Python
10	yk7333/d3po [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion...	39	Emerging	244	Python
11	czg1225/AsyncDiff [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising	39	Emerging	212	Python
12	mapo-t2i/mapo Official codebase for Margin-aware Preference Optimization for Aligning...	37	Emerging	82	Python
13	MiZhenxing/ThinkDiff ICML2025, I Think, Therefore I Diffuse: Enabling Multimodal In-Context...	37	Emerging	192	Python
14	HKUDS/DiffKG [WSDM'2024 Oral] "DiffKG: Knowledge Graph Diffusion Model for Recommendation"	37	Emerging	134	Python
15	HKUDS/RecDiff [CIKM'2024] "RecDiff: Diffusion Model for Social Recommendation"	36	Emerging	89	Python
16	yjyddq/EOSER-ASS-RL Official Repository of "Taming Masked Diffusion Language Models via...	36	Emerging	27	Python
17	mihirp1998/AlignProp AlignProp uses direct reward backpropogation for the alignment of...	35	Emerging	314	Python
18	InternScience/AdaptiveDiffusion [NeurIPS'24] Training-Free Adaptive Diffusion with Bounded Difference...	35	Emerging	73	Python
19	basiclab/DiffusionDRO [NeurIPS 2025] Ranking-based Preference Optimization for Diffusion Models...	34	Emerging	7	Python
20	Ting-Justin-Jiang/sada-icml [ICML 2025] Official Repo for Stability-guided Adaptive Diffusion...	34	Emerging	39	Python
21	keshik6/grafting [NeurIPS 2025 Oral] Official Code for Exploring Diffusion Transformer...	34	Emerging	72	Jupyter Notebook
22	aaron-di/CDM-PSL [AAAI 2025] CDM-PSL: Expensive Multi-Objective Bayesian Optimization Based...	33	Emerging	3	Python
23	H-EmbodVis/EasyCache Less is Enough: Training-Free Video Diffusion Acceleration via...	33	Emerging	290	Python
24	hu-zijing/B2-DiffuRL [CVPR 25] A framework named B^2-DiffuRL for RL-based diffusion model fine-tuning.	33	Emerging	53	Python
25	masa-ue/SVDD Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding....	33	Emerging	37	Python
26	AniAggarwal/ecad [ICLR 2026] Code for Evolutionary Caching to Accelerate Your Off-the-Shelf...	33	Emerging	31	Python
27	ZiyiZhang27/sdpo [IEEE TPAMI] Code for the paper "Aligning Few-Step Diffusion Models with...	32	Emerging	19	Python
28	BIT-DA/DUSA [NeurIPS 2024] Exploring Structured Semantic Priors Underlying Diffusion...	30	Emerging	22	Python
29	ilog-ecnu/CDM-PSL [AAAI 2025] CDM-PSL: Expensive Multi-Objective Bayesian Optimization Based...	30	Emerging	6	Python
30	AIDC-AI/Diffusion-SDPO Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models	29	Experimental	21	Python
31	L-YeZhu/BoundaryDiffusion [NeurIPS2023] BoundaryDiffusion: A learning-free method for semantic control...	29	Experimental	40	Python
32	hu-zijing/D-Fusion [ICML 25] Denoising trajectory fusion, a method to construct RL-trainable...	29	Experimental	11	Python
33	user683/CausalDiffRec [WWW'25]The official implementation of Graph Representation Learning via...	29	Experimental	18	Python
34	ModelTC/HarmoniCa [ICML 2025] This is the official PyTorch implementation of "🎵 HarmoniCa:...	28	Experimental	45	Python
35	masa-ue/RLfinetuning_Diffusion_Bioseq Code for the tutorial/review paper for RL-based-fine-tuniing. In this code,...	28	Experimental	158	Jupyter Notebook
36	OptiSys-ZJU/segquant [CVPR '26] A Semantics-Aware and Generalizable Quantization Framework for...	28	Experimental	2	Python
37	akashsonowal/ddpo-pytorch RLHF for Stable Diffusion	27	Experimental	14	Python
38	zihaowu25/InvarDiff InvarDiff: Cross-Scale Invariance Caching for Accelerated Diffusion Models	26	Experimental	4	Python
39	ZiyiZhang27/tdpo [ICML 2024] Code for the paper "Confronting Reward Overoptimization for...	26	Experimental	38	Python
40	yjyddq/rho-EOS Official Repository of "ρ-𝙴𝙾𝚂: Training-free Bidirectional Variable-Length...	25	Experimental	5	Python
41	itsluckysharma01/RL-based_Adaptive_Game_Difficulty_Engine This repository contains an implementation of a 🏗️Reinforcement Learning...	25	Experimental	2	Python
42	HKUDS/DiffMM [ACM MM'2024]"DiffMM: Multi-Modal Diffusion Model for Recommendation"	25	Experimental	99	Python
43	horseee/learning-to-cache [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via...	23	Experimental	118	Python
44	UCF-CRCV/core Context-Robust Remasking for Diffusion Language Models	23	Experimental	2	Python
45	zhaoyl18/SEIKO SEIKO is a novel reinforcement learning method to efficiently fine-tune...	23	Experimental	30	Python
46	suinleelab/An-Efficient-Framework-for-Crediting-Data-Contributors-of-Diffusion-Models [ICLR2025] An Efficient Framework for Crediting Data Contributors of Diffusion Models	23	Experimental	2	Jupyter Notebook
47	sahsaeedi/DCPO-T2I [TMLR] Dual Caption Preference Optimization	21	Experimental	9	Python
48	LemonTwoL/ReNeg ReNeg: Learning Negative Embedding with Reward Guidance	21	Experimental	35	Python
49	Yeez-lee/Data-Selection-and-Reweighting-for-Diffusion-Models [ICASSP 25'] Pruning then Reweighting: Towards Data-Efficient Training of...	20	Experimental	2	—
50	THU-AccDiff/xslim Official implementation of X-Slim(xslim): Accelerating diffusion model via...	19	Experimental	8	Python
51	federicobrancasi/quantdiff-paper Research paper: QuantDiff - Efficient Mixed-Precision Quantization for...	19	Experimental	—	TeX
52	arthur-x/AlmostPerfect Simple end-to-end RLHF (Reinforcement Learning from Human Feedback) for...	17	Experimental	1	Python
53	jinluo12345/Reinforcement-learning-guidance RLG: Inference-Time Alignment Control for Diffusion Models with...	14	Experimental	11	Python
54	IDavron/RWR Implementation of Reward Weighted Regression method proposed in "Training...	11	Experimental	3	Jupyter Notebook
55	LIUTIGHE/HetCache [CVPR'26] The official implementation of paper "Accelerating Diffusion-based...	11	Experimental	—	—
56	KJLdefeated/MODDPO 2024 NYCU DLP Final Project: Training Diffusion Model with Multi-Objective...	10	Experimental	2	Python
57	Alsace08/RetroDiff [AISTATS 2025] Code and Data Repo for Paper "RetroDiff: Retrosynthesis as...	10	Experimental	2	Python