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.
☆29Updated 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…☆156Updated last year
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction☆35Updated 2 years ago
- Inference-Time Alignment in Protein Diffusion Models☆49Updated 11 months ago
- Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (…☆36Updated last year
- Simple Guidance Mechanisms for Discrete Diffusion Models☆65Updated last year
- ☆41Updated last year
- Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching☆59Updated 7 months ago
- Official Code for Local Search GFlowNets (ICLR 2024 Spotlight)☆24Updated 10 months ago
- Code for the paper: "Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods"☆31Updated 7 months ago
- 📰 Must-Read Papers on Offline Model-Based Optimization 🔥☆29Updated 6 months ago
- Code repository for Trajectory Flow Matching☆96Updated last year
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆84Updated 8 months ago
- Official Jax Implementation of MD4 Masked Diffusion Models☆151Updated 10 months ago
- ☆25Updated last year
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction (ICML 2023)☆50Updated 2 years ago
- Implementation of Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models☆75Updated 2 years ago
- Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"☆64Updated 8 months ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆204Updated 6 months ago
- ☆36Updated 9 months ago
- Entropic Optimal Transport Benchmark (NeurIPS 2023).☆27Updated last year
- Repository for "Generative Flow Networks as Entropy-Regularized RL" (AISTATS-2024, Oral)☆40Updated last year
- code for "Generalized Schrödinger Bridge Matching" (ICLR 2024).☆84Updated last year
- Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold☆69Updated 10 months ago
- Code release for "Stochastic Optimal Control Matching"☆39Updated last year
- [ICML 2025] The official implementation of the paper "On the Guidance of Flow Matching"☆71Updated 3 months ago
- Code for paper "Compositional Sculpting of Iterative Generative Processes"☆25Updated 2 years ago
- GflowNets, MCMC, Metropolis-Hasting, Gibbs sampling, Metropolis-adjusted Langevin, Inverse Transform Sampling, Acceptance-Rejection Metho…☆86Updated 2 years ago
- ☆28Updated 2 years ago
- ☆32Updated 2 years ago
- The Superposition of Diffusion Models Using the Itô Density Estimator☆50Updated 9 months ago