mlfoundations / open-diffusionLinks
Simple large-scale training of stable diffusion with multi-node support.
☆131Updated 2 years ago
Alternatives and similar repositories for open-diffusion
Users that are interested in open-diffusion are comparing it to the libraries listed below
Sorting:
- Iterable datapipelines for pytorch training.☆82Updated 9 months ago
- ☆171Updated last year
- Open reproduction of MUSE for fast text2image generation.☆350Updated last year
- Diffusion Reinforcement Learning Library☆185Updated last year
- JAX implementation ViT-VQGAN☆83Updated 2 years ago
- [ICLR 2025] Official PyTorch implmentation of paper "T-Stitch: Accelerating Sampling in Pre-trained Diffusion Models with Trajectory Stit…☆102Updated last year
- MoVQGAN - model for the image encoding and reconstruction☆240Updated last year
- 🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…☆79Updated 5 months ago
- CLOOB training (JAX) and inference (JAX and PyTorch)☆71Updated 3 years ago
- ☆53Updated 2 years ago
- An in-context conditioning version of MUSE with pre-trained checkpoints.☆110Updated 2 years ago
- Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"☆173Updated 11 months ago
- AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more samp…☆285Updated 7 months ago
- ☆103Updated last year
- A Video Tokenizer Evaluation Dataset☆118Updated 4 months ago
- Code for instruction-tuning Stable Diffusion.☆232Updated last year
- A one-stop library to standardize the inference and evaluation of all the conditional image generation models. (ICLR 2024)☆167Updated last month
- Huggingface-compatible SDXL Unet implementation that is readily hackable☆423Updated last year
- Reproduction of DDPO paper (RLHF for diffusion)☆84Updated last year
- ☆85Updated last year
- Official implementation of "Controlling Text-to-Image Diffusion by Orthogonal Finetuning".☆292Updated 7 months ago
- Train VAE like a boss☆279Updated 7 months ago
- Faster generation with text-to-image diffusion models.☆214Updated 7 months ago
- Let's make a video clip☆92Updated 2 years ago
- ☆72Updated 2 years ago
- Educational repository for applying the main video data curation techniques presented in the Stable Video Diffusion paper.☆82Updated last year
- [NeurIPS 2023] This repository includes the official implementation of our paper "An Inverse Scaling Law for CLIP Training"☆314Updated last year
- Efficiently read embedding in streaming from any filesystem☆98Updated last year
- Get hundred of million of image+url from the crawling at home dataset and preprocess them☆219Updated last year
- ☆30Updated last year