Stars
③[ICML2024] [IQA, IAA, VQA] All-in-one Foundation Model for visual scoring. Can efficiently fine-tune to downstream datasets.
FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
[NeurIPS 2025 DB] OneIG-Bench is a meticulously designed comprehensive benchmark framework for fine-grained evaluation of T2I models across multiple dimensions, including subject-element alignment,…
Discrete Flow Matching implemented in PyTorch
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
An educational resource to help anyone learn deep reinforcement learning.
PyTorch code and models for VJEPA2 self-supervised learning from video.
Offical implementation for "Probability Density Geodesics in Image Diffusion Latent Space" (CVPR2025)
Official repository for "AM-RADIO: Reduce All Domains Into One"
[ICCV 2025] Official implementation of the paper: REPA-E: Unlocking VAE for End-to-End Tuning of Latent Diffusion Transformers
[ICLR 2025] Pyramidal Flow Matching for Efficient Video Generative Modeling
Official Repo for Paper "OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision" [ICLR2025]
Illumination Drawing Tools for Text-to-Image Diffusion Models
Model Compression Toolbox for Large Language Models and Diffusion Models
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340
Efficient vision foundation models for high-resolution generation and perception.
Collection of helpful utilities for Manim. Now dual compatible with both editions!
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
⚡ A Fast, Extensible Progress Bar for Python and CLI
Official inference repo for FLUX.1 models
PyTorch code and models for V-JEPA self-supervised learning from video.