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.
☆26Updated 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…☆148Updated last year
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction☆35Updated last year
- Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (…☆33Updated last year
- Inference-Time Alignment in Protein Diffusion Models☆44Updated 8 months ago
- ☆36Updated last year
- Code for the paper: "Fine-Tuning Discrete Diffusion Models with Policy Gradient Methods"☆27Updated 4 months ago
- Simple Guidance Mechanisms for Discrete Diffusion Models☆52Updated 9 months ago
- Official Code for Local Search GFlowNets (ICLR 2024 Spotlight)☆23Updated 7 months ago
- Official Jax Implementation of MD4 Masked Diffusion Models☆128Updated 7 months ago
- Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching☆44Updated 4 months ago
- Implementation of Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models☆71Updated last year
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction （ICML 2023）☆50Updated 2 years ago
- 📰 Must-Read Papers on Offline Model-Based Optimization 🔥☆24Updated 3 months ago
- Code repository for Trajectory Flow Matching☆83Updated 11 months ago
- ☆25Updated last year
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆187Updated 3 months ago
- Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"☆61Updated 5 months ago
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆79Updated 5 months ago
- Code release for "Stochastic Optimal Control Matching"☆37Updated last year
- Entropic Optimal Transport Benchmark (NeurIPS 2023).☆26Updated last year
- ☆33Updated 6 months ago
- Code for "Optimizing DDPM Sampling with Shortcut Fine-Tuning" (https://arxiv.org/abs/2301.13362), ICML 2023☆30Updated 2 years ago
- Official Code for Learning to Sample Effective and Diverse Prompts for Text-to-Image Generation (CVPR 2025)☆11Updated 6 months ago
- Code for paper "Compositional Sculpting of Iterative Generative Processes"☆24Updated 2 years ago
- ☆33Updated last year
- Source code for "Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference." In NeurIPS 2024☆18Updated 10 months ago
- Code for the paper Iterated Denoising Energy Matching for Sampling from Boltzmann Densities.☆63Updated 6 months ago
- Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold☆64Updated 7 months ago
- Graph Diffusion Policy Optimization☆40Updated last year
- GflowNets, MCMC, Metropolis-Hasting, Gibbs sampling, Metropolis-adjusted Langevin, Inverse Transform Sampling, Acceptance-Rejection Metho…☆86Updated 2 years ago