Publications
Publications
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
An open-source world model for controllable minute-long 720p video generation on a single GPU.
LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution
UltraFlux: Data-Model Co-Design for High-quality Native 4K Text-to-Image Generation across Diverse Aspect Ratios
Native 4K text-to-image generation across diverse aspect ratios, matching or surpassing Seedream 4.0.
LucidFlux: Caption-Free Universal Image Restoration via a Large-Scale Diffusion Transformer
A caption-free 14B restoration model delivering photorealistic results beyond leading commercial systems.
GlassWizard: Harvesting Diffusion Priors for Glass Surface Detection
MagicInfinite: Generating Infinite Talking Videos with Your Words and Voice
Technical report for Hedra Inc.’s Character-3 model.
AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image Enhancement
PromptHaze: Prompting Real-world Dehazing via Depth Anything Model
Learning Diffusion Texture Priors for Image Restoration
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
The first SDXL-level high-resolution non-AR T2I model.