Stars
Code for Learning to Refocus with Video Diffusion Models - SIGGRAPH ASIA 2025
[AAAI 2026] Generating Weather in any 3D Gaussian Scene
Towards Scalable Pre-training of Visual Tokenizers for Generation
Ovis-Image is a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints.
SigLIP-based Aesthetic Score Predictor
AAAI2026 X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learning
Official repository for “DeCo: Frequency-Decoupled Pixel Diffusion for End-to-End Image Generation”
Official Implementation of "UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation"
This project is the official implementation of "UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation"
Official repository for the paper "MICo-150K: A Comprehensive Dataset for Multi-Image Composition".
Light-X: Generative 4D Video Rendering with Camera and Illumination Control
This is the official repository for "BokehDiff: Neural Lens Blur with One-Step Diffusion" (ICCV'25).
UniCombine: Unified Multi-Conditional Combination with Diffusion Transformer
Official Implementation of "Flare7K: A Phenomenological Nighttime Flare Removal Dataset"
GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)
Official inference repo for FLUX.2 models
https://little-misfit.github.io/GRAG-Image-Editing/
ChronoEdit: Towards Temporal Reasoning for Image Editing and World Simulation
🎨 A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
[CVPR 2025 Highlight] Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis
[NeurIPS 2025] Native-resolution diffusion Transformer
Official Repo for Paper <WEAVE: Unleashing and Benchmarking the Interleaved Cross-modality Comprehension and Generation>