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…☆144Updated 10 months ago
- Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (…☆32Updated 10 months ago
- Inference-Time Alignment in Protein Diffusion Models☆40Updated 6 months ago
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction☆33Updated last year
- Simple Guidance Mechanisms for Discrete Diffusion Models☆48Updated 7 months ago
- ☆24Updated last year
- Implementation of Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models☆71Updated last year
- Code for the paper: "Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods"☆27Updated 2 months ago
- Official Jax Implementation of MD4 Masked Diffusion Models☆120Updated 5 months ago
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆70Updated 3 months ago
- Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"☆57Updated 3 months ago
- Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching☆40Updated 2 months ago
- Code for the paper Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.☆58Updated 3 months ago
- Official Code for Local Search GFlowNets (ICLR 2024 Spotlight)☆20Updated 5 months ago
- ☆18Updated 2 years ago
- ☆35Updated 4 months ago
- Code for the paper https://arxiv.org/abs/2402.04997☆88Updated last year
- ☆32Updated last year
- Educational implementation of the Discrete Flow Matching paper☆101Updated 11 months ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆174Updated last month
- Code for our paper "Unlocking Guidance for Discrete State-Space Diffusion and Flow Models"☆23Updated 3 months ago
- GflowNets, MCMC, Metropolis-Hasting, Gibbs sampling, Metropolis-adjusted Langevin, Inverse Transform Sampling, Acceptance-Rejection Metho…☆86Updated 2 years ago
- [ICML 2025] The official implementation of the paper "On the Guidance of Flow Matching"☆46Updated this week
- 📰 Must-Read Papers on Offline Model-Based Optimization 🔥☆24Updated last month
- ☆31Updated 2 years ago
- ☆34Updated last year
- Code release for "Stochastic Optimal Control Matching"☆36Updated 11 months ago
- Code for our paper "Generative Flow Networks for Discrete Probabilistic Modeling"☆85Updated 2 years ago
- Entropic Optimal Transport Benchmark (NeurIPS 2023).☆24Updated last year
- Unofficial PyTorch implementation of Discrete Denoising Diffusion Probabilistic Model(D3PM)☆39Updated 2 years ago