Highlights
- Pro
Stars
"SlimFlow: Training Smaller One-Step Diffusion Models with Rectified Flow", Yuanzhi Zhu, Xingchao Liu, Qiang Liu
An open-source toolbox for fast sampling of diffusion models. Official implementations for our [CVPR-2024, ICML-2024] papers
(CVPR 2024) 🧩 TokenCompose: Text-to-Image Diffusion with Token-level Supervision
Mixed continous/categorical flow-matching model for de novo molecule generation.
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Open-Sora: Democratizing Efficient Video Production for All
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
[IJCAI 2022, Official Code] for paper "Rethinking Image Aesthetics Assessment: Models, Datasets and Benchmarks". Official Weights and Demos provided. 首个面向多主题场景的美学评估数据集、算法和benchmark.
Official code for paper: Text-to-Image Rectified Flow as Plug-and-Play Priors
The codebase of our paper "Improving the Training of Rectified Flows"
[ICLR 2024] Official implementation of Bellman Optimal Stepsize Straightening of Flow-Matching Models
Hunyuan-DiT : A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding
Denoising Diffusion Step-aware Models (ICLR2024)
StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
PyTorch implementation of CLIP Maximum Mean Discrepancy (CMMD) for evaluating image generation models.
[ICML 2024] Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs (PRG)
[CVPR'24 Highlight] The official code and data for paper "EgoThink: Evaluating First-Person Perspective Thinking Capability of Vision-Language Models"
[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
[ECCV 2024] Official Repository for DiffiT: Diffusion Vision Transformers for Image Generation
[NeurIPS 2023] Formulating Discrete Probability Flow Through Optimal Transport
FoldFlow: SE(3)-Stochastic Flow Matching for Protein Backbone Generation