kvablack / ddpo-pytorch
DDPO for finetuning diffusion models, implemented in PyTorch with LoRA support
☆435Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for ddpo-pytorch
- Code for the paper "Training Diffusion Models with Reinforcement Learning"☆356Updated last year
- Code for "Diffusion Model Alignment Using Direct Preference Optimization"☆270Updated 10 months ago
- [CVPR 2024] Code for the paper "Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model"☆173Updated 7 months ago
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆242Updated 3 weeks ago
- ☆456Updated last year
- ☆211Updated last year
- code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆616Updated last week
- Analyzing and Improving the Training Dynamics of Diffusion Models (EDM2)☆533Updated 5 months ago
- Code for Fast Training of Diffusion Models with Masked Transformers☆375Updated 6 months ago
- A mini-library for training consistency models.☆215Updated 10 months ago
- Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"☆692Updated 8 months ago
- Unofficial Implementation of Consistency Models in pytorch☆251Updated last year
- Implementation of MagViT2 Tokenizer in Pytorch☆564Updated last month
- 🚀 PyTorch Implementation of "Progressive Distillation for Fast Sampling of Diffusion Models(v-diffusion)"☆219Updated 2 years ago
- ☆201Updated last month
- ☆239Updated last month
- ☆446Updated 9 months ago
- Creating a diffusion model from scratch in PyTorch to learn exactly how they work.☆329Updated 6 months ago
- Implementation of a single layer of the MMDiT, proposed in Stable Diffusion 3, in Pytorch☆256Updated 2 months ago
- Official Implementation of Rectified Flow (ICLR2023 Spotlight)☆960Updated 4 months ago
- Minimal implementation of scalable rectified flow transformers, based on SD3's approach☆445Updated 4 months ago
- Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis☆400Updated 5 months ago
- Better Aligning Text-to-Image Models with Human Preference. ICCV 2023☆267Updated last year
- [ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation☆459Updated 3 weeks ago
- MoVQGAN - model for the image encoding and reconstruction☆201Updated last year
- Consistency Models Made Easy☆226Updated last month
- This repo contains the code for 1D tokenizer and generator☆554Updated this week
- [ICCV 2023] Efficient Diffusion Training via Min-SNR Weighting Strategy☆229Updated 7 months ago
- Official Pytorch Implementation of Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think☆674Updated last week
- Implementation of Classifier Free Guidance in Pytorch, with emphasis on text conditioning, and flexibility to include multiple text embed…☆365Updated last month