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…☆155Updated 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☆48Updated 11 months ago
- Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (…☆35Updated last year
- Simple Guidance Mechanisms for Discrete Diffusion Models☆64Updated last year
- Implementation of Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models☆73Updated 2 years ago
- ☆40Updated last year
- Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching☆57Updated 6 months ago
- Official Code for Local Search GFlowNets (ICLR 2024 Spotlight)☆24Updated 9 months ago
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆84Updated 7 months ago
- Code repository for Trajectory Flow Matching☆94Updated last year
- Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"☆63Updated 7 months ago
- ☆25Updated last year
- 📰 Must-Read Papers on Offline Model-Based Optimization 🔥☆29Updated 5 months ago
- Code for the paper: "Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods"☆28Updated 7 months ago
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction （ICML 2023）☆50Updated 2 years ago
- Official Jax Implementation of MD4 Masked Diffusion Models☆149Updated 9 months ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆200Updated 5 months ago
- Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold☆69Updated 9 months ago
- [ICML 2025] The official implementation of the paper "On the Guidance of Flow Matching"☆68Updated 3 months ago
- Code for paper "Compositional Sculpting of Iterative Generative Processes"☆25Updated 2 years ago
- ☆37Updated last year
- Official Implementation for Inference-time Scaling of Diffusion Models through Classical Search☆25Updated 2 months ago
- ☆35Updated 8 months ago
- Code for GFlowNet-EM, a novel algorithm for fitting latent variable models with compositional latents and an intractable true posterior.☆41Updated last year
- Code release for "Stochastic Optimal Control Matching"☆39Updated last year
- The Superposition of Diffusion Models Using the Itô Density Estimator☆51Updated 9 months ago
- Code for the paper Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.☆67Updated 8 months ago
- Code for our paper "Unlocking Guidance for Discrete State-Space Diffusion and Flow Models"☆31Updated 8 months ago
- ☆25Updated last year