DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support
☆768Mar 22, 2024Updated 2 years ago
Alternatives and similar repositories for ddpo-pytorch
Users that are interested in ddpo-pytorch are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for the paper "Training Diffusion Models with Reinforcement Learning"☆574Jul 5, 2023Updated 3 years ago
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆324Nov 1, 2024Updated last year
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆244Apr 6, 2024Updated 2 years ago
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆706Jun 2, 2026Updated last month
- [NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation☆1,695Oct 29, 2025Updated 9 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆677May 24, 2024Updated 2 years ago
- [NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL☆2,437May 7, 2026Updated 2 months ago
- ☆22Oct 20, 2023Updated 2 years ago
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆39May 9, 2024Updated 2 years ago
- ☆601Dec 21, 2024Updated last year
- Reproduction of DDPO paper (RLHF for diffusion)☆94Sep 20, 2023Updated 2 years ago
- [CVPR 2025] Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization☆271Apr 7, 2025Updated last year
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆293Jul 14, 2023Updated 3 years ago
- An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation☆1,642Oct 16, 2025Updated 9 months ago
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- ☆74Sep 23, 2025Updated 10 months ago
- RichHF-18K dataset contains rich human feedback labels we collected for our CVPR'24 paper: https://arxiv.org/pdf/2312.10240, along with t…☆157Jun 25, 2024Updated 2 years ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆83Jun 11, 2024Updated 2 years ago
- Code for the tutorial/review paper for RL-based-fine-tuniing. In this code, we especially focus on the design of biological sequences li…☆159Sep 15, 2024Updated last year
- Video Diffusion Alignment via Reward Gradients. We improve a variety of video diffusion models such as VideoCrafter, OpenSora, ModelScope…☆315Mar 12, 2025Updated last year
- [NeurIPS 2025] Improving Video Generation with Human Feedback☆489Sep 24, 2025Updated 10 months ago
- Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation☆1,960Aug 15, 2024Updated last year
- [IJCV] FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention☆715Jan 10, 2025Updated last year
- [ICLR'25 Oral] Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆1,681Mar 16, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- SEIKO is a novel reinforcement learning method to efficiently fine-tune diffusion models in an online setting. Our methods outperform all…☆30Jul 18, 2024Updated 2 years ago
- ☆58Sep 23, 2024Updated last year
- official repo for "VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation" [EMNLP2024]☆121Dec 4, 2025Updated 7 months ago
- [ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process☆990Feb 10, 2026Updated 5 months ago
- GenEval: An object-focused framework for evaluating text-to-image alignment☆472Mar 3, 2025Updated last year
- [SIGGRAPH Asia 2024] ReVersion: Diffusion-Based Relation Inversion from Images☆503Oct 7, 2025Updated 9 months ago
- [NeurIPS 2024] ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization☆166Sep 15, 2025Updated 10 months ago
- Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"☆1,191Dec 22, 2025Updated 7 months ago
- Consistency Distilled Diff VAE☆2,213Nov 7, 2023Updated 2 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"☆8,693May 31, 2024Updated 2 years ago
- Code for "Optimizing DDPM Sampling with Shortcut Fine-Tuning" (https://arxiv.org/abs/2301.13362), ICML 2023☆30Oct 6, 2023Updated 2 years ago
- CLIP+MLP Aesthetic Score Predictor☆1,328Jul 1, 2024Updated 2 years ago
- (NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis☆1,415Mar 5, 2025Updated last year
- [AAAI 2026] VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation☆422Mar 26, 2025Updated last year
- A curated list of Diffusion Model in RL resources (continually updated)☆1,630May 30, 2026Updated last month
- Official implementation of UnifiedReward & [NeurIPS 2025] UnifiedReward-Think & UnifiedReward-Flex☆796Jun 18, 2026Updated last month