An official implementation of FlashI2V.

Official Code of "VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning"

[NeurIPS 2025 🔥] Official impl. of "AlignedGen: Aligning Style Across Generated Images". An ultra-simple, user-friendly yet state-of-the-art codebase for style-aligned image generation!

Official repository for the UAE paper, unified-GRPO, and unified-Bench

[Arxiv'25] IC-Custom: Diverse Image Customization via In-Context Learning

Official implementation of the paper "GenCompositor: Generative Video Compositing with Diffusion Transformer"

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

(CVPR 2025) Adversarial Diffusion Compression for Real-World Image Super-Resolution [PyTorch]

Repo for SeedVR2 & SeedVR (CVPR2025 Highlight)

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

This repository provides valuable reference for researchers in the field of multimodality, please start your exploratory travel in RL-based Reasoning MLLMs!

[NeurIPS 2025 Spotlight] Q-Insight: Understanding Image Quality via Visual Reinforcement Learning

[NeurIPS 2025 Spotlight] VisualQuality-R1 is the first open-sourced NR-IQA model can accurately describe and rate the image quality.

Official implementation of BLIP3o-Series

[ICCV2025] PyTorch implementation of "Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models"

Official code for our CVPR 2025 paper: "Toward Generalized Image Quality Assessment: Relaxing the Perfect Reference Quality Assumption"

MAGI-1: Autoregressive Video Generation at Scale

Q-Insight is open-sourced at https://github.com/bytedance/Q-Insight. This repository will not receive further updates.

[ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos

[ICLR 2025] Autoregressive Video Generation without Vector Quantization

[NeurIPS 2024] OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding

Official code of "Imagine360: Immersive 360 Video Generation from Perspective Anchor"

[SIGGRAPH 2025] LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation"

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis