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.
☆31Jul 18, 2024Updated 2 years ago
Alternatives and similar repositories for SEIKO
Users that are interested in SEIKO are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Derivative-Free, Training-Free, Guidance in Diffusion Models☆16Sep 30, 2024Updated last year
- Code for paper: "Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design"☆78May 10, 2025Updated last year
- [NeurIPS 2023] Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement☆18Oct 30, 2024Updated last year
- Derivative-Free Guidance in Diffusion Models with Soft Value-Based Decoding. For controlled generation in DNA, RNA, proteins, molecules (…☆40Jan 7, 2026Updated 8 months ago
- Code for the tutorial/review paper for RL-based-fine-tuniing. In this code, we especially focus on the design of biological sequences li…☆160Sep 15, 2024Updated 2 years ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Code for the paper "Molecule Design by Latent Space Energy-based Modeling and Gradual Distribution Shifting" in UAI 2023☆15Nov 15, 2023Updated 2 years ago
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆328Nov 1, 2024Updated last year
- Computational analysis of nucleic acids structures using graph neural networks☆16Mar 25, 2024Updated 2 years ago
- Inference-Time Alignment in Protein Diffusion Models☆59Jan 7, 2026Updated 8 months ago
- The collection of my research papers' illustrations.☆21Oct 15, 2023Updated 2 years ago
- Official code repository for the paper Exploring Chemical Space with Score-based Out-of-distribution Generation (ICML 2023)☆41May 19, 2024Updated 2 years ago
- The official implementation of Diffusion-KTO: Aligning Diffusion Models by Optimizing Human Utility☆67Aug 16, 2025Updated last year
- ☆34Jul 10, 2023Updated 3 years ago
- Code base for paper: Reparameterized Policy Learning for Multimodal Trajectory Optimization☆28Jul 19, 2023Updated 3 years ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Subtask-Aware Visual Reward Learning from Segmented Demonstrations (ICLR 2025 accepted)☆20Apr 11, 2025Updated last year
- Official Code for Local Search GFlowNets (ICLR 2024 Spotlight)☆25Feb 27, 2025Updated last year
- DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support☆777Mar 22, 2024Updated 2 years ago
- Official Code for Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization (NIPS 2024)☆23Aug 15, 2024Updated 2 years ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆236Jun 26, 2025Updated last year
- ☆58Sep 23, 2024Updated 2 years ago
- Code for the paper "Training Diffusion Models with Reinforcement Learning"☆579Jul 5, 2023Updated 3 years ago
- Benchmarks for Model-Based Optimization☆96Apr 21, 2024Updated 2 years ago
- Generative models and other stuff too, maybe, perhaps even probably☆16Dec 12, 2015Updated 10 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction☆36Nov 3, 2023Updated 2 years ago
- Code of the paper "Universal Morphology Control via Contextual Modulation" at ICML 2023☆17Aug 3, 2023Updated 3 years ago
- An official 're'-implementation of Physics-induced graph neural network: An application to wind-farm power estimation (PGNN).☆29Jul 27, 2021Updated 5 years ago
- DL reading group arrangements☆22Sep 2, 2025Updated last year
- Official repository for GFACS☆38May 17, 2024Updated 2 years ago
- Offline Reinforcement Learning Reading Group☆27Nov 22, 2022Updated 3 years ago
- Official codebase for GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning.☆32Nov 12, 2024Updated last year
- ☆61Apr 7, 2026Updated 5 months ago
- Source code for "A Dense Reward View on Aligning Text-to-Image Diffusion with Preference" (ICML'24).☆38May 9, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆11Feb 26, 2024Updated 2 years ago
- Flexible modulation of sequence generation in the entorhinal-hippocampal system.☆13Apr 5, 2022Updated 4 years ago
- Anti exploration in offline reinforcement learning☆11May 17, 2021Updated 5 years ago
- Course Website for "AI618: Generative Model and Unsupervised Learning"☆36May 23, 2023Updated 3 years ago
- dynamic planning, hybrid models, hierarchical active inference, tool use☆15Jun 13, 2025Updated last year
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆84Jun 11, 2024Updated 2 years ago
- ☆13Aug 14, 2022Updated 4 years ago