tmabraham / ddpo-pytorch
Reproduction of DDPO paper (RLHF for diffusion)
☆81Updated last year
Alternatives and similar repositories for ddpo-pytorch:
Users that are interested in ddpo-pytorch are comparing it to the libraries listed below
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆269Updated 3 months ago
- [ICML 2023] Reflected Diffusion Models (https://arxiv.org/abs/2304.04740)☆157Updated last year
- My take on Flow Matching☆36Updated last month
- Diffusion Reinforcement Learning Library☆179Updated last year
- Unofficial Implementation of Consistency Models in pytorch☆255Updated last year
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆84Updated last month
- Simple large-scale training of stable diffusion with multi-node support.☆128Updated last year
- ☆51Updated last year
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆190Updated 10 months ago
- ☆50Updated 4 months ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆67Updated 8 months ago
- PyTorch implementation of CLIP Maximum Mean Discrepancy (CMMD) for evaluating image generation models.☆114Updated 10 months ago
- This is the official repo for the paper "Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles", Tang et…☆196Updated last year
- Implementation of a multimodal diffusion transformer in Pytorch☆99Updated 7 months ago
- Implementation of the video diffusion model and training scheme presented in the paper, Flexible Diffusion Modeling of Long Videos, in Py…☆84Updated 2 years ago
- Official implementation of the paper The Hidden Language of Diffusion Models☆70Updated last year
- Focused on fast experimentation and simplicity☆65Updated last month
- ☆72Updated last year
- Train VAE like a boss☆264Updated 3 months ago
- ☆46Updated 3 months ago
- 🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…☆67Updated last month
- ☆83Updated last year
- Official implementation of the paper "Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models☆165Updated last year
- Code for the paper "Training Diffusion Models with Reinforcement Learning"☆389Updated last year
- Ablating Concepts in Text-to-Image Diffusion Models (ICCV 2023)☆153Updated last month
- Official PyTorch Implementation of "Learning to Learn with Generative Models of Neural Network Checkpoints"☆337Updated 2 years ago
- FMBoost: Boosting Latent Diffusion with Flow Matching (ECCV 2024 Oral)☆218Updated 2 months ago
- Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video without cascading networks, in P…☆200Updated last year
- PyTorch implementation for "Parallel Sampling of Diffusion Models", NeurIPS 2023 Spotlight☆129Updated last year
- JAX implementation ViT-VQGAN☆80Updated 2 years ago