zhaoyl18 / SEIKOLinks
SEIKO is a novel reinforcement learning method to efficiently fine-tune diffusion models in an online setting. Our methods outperform all baselines (PPO, classifier-based guidance, direct reward backpropagation) for fine-tuning Stable Diffusion.
☆23Updated last year
Alternatives and similar repositories for SEIKO
Users that are interested in SEIKO are comparing it to the libraries listed below
Sorting:
- Code for the tutorial/review paper for RL-based-fine-tuniing. In this code, we especially focus on the design of biological sequences li…☆146Updated 11 months ago
- Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (…☆33Updated 10 months ago
- Inference-Time Alignment in Protein Diffusion Models☆42Updated 7 months ago
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction☆33Updated last year
- Official Code for Local Search GFlowNets (ICLR 2024 Spotlight)☆21Updated 6 months ago
- Implementation of Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models☆71Updated last year
- Simple Guidance Mechanisms for Discrete Diffusion Models☆50Updated 8 months ago
- ☆33Updated last year
- Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"☆59Updated 3 months ago
- Code for the paper: "Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods"☆27Updated 3 months ago
- ☆24Updated last year
- Code repository for Trajectory Flow Matching☆78Updated 10 months ago
- Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching☆40Updated 3 months ago
- Code for the paper Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.☆59Updated 4 months ago
- 📰 Must-Read Papers on Offline Model-Based Optimization 🔥☆24Updated 2 months ago
- Code release for "Stochastic Optimal Control Matching"☆37Updated last year
- Official Jax Implementation of MD4 Masked Diffusion Models☆123Updated 6 months ago
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆74Updated 4 months ago
- Code for the paper https://arxiv.org/abs/2402.04997☆91Updated last year
- Entropic Optimal Transport Benchmark (NeurIPS 2023).☆24Updated last year
- code for "Generalized Schrödinger Bridge Matching" (ICLR 2024).☆77Updated last year
- Code for our paper "Unlocking Guidance for Discrete State-Space Diffusion and Flow Models"☆27Updated 4 months ago
- ☆34Updated 5 months ago
- [ICML 2025] The official implementation of the paper "On the Guidance of Flow Matching"☆49Updated 3 weeks ago
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction (ICML 2023)☆48Updated 2 years ago
- ☆34Updated last year
- ☆31Updated 2 months ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆176Updated 2 months ago
- Official PyTorch implementation for "Unifying Bayesian Flow Networks and Diffusion Models through Stochastic Differential Equations"☆40Updated last year
- PyTorch implementation for our ICLR 2024 paper "Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory…☆24Updated last year