#
Lists (1)
Starred repositories
Enjoy the magic of Diffusion models!
Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition
Qwen-Image-Lightning: Speed up Qwen-Image model with distillation
MiroThinker is open-source agentic models trained for deep research and complex tool use scenarios.
T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation (ICCV'25)
Official inference code and LongText-Bench benchmark for our paper X-Omni (https://arxiv.org/pdf/2507.22058).
Wan: Open and Advanced Large-Scale Video Generative Models
Official implementation for CVPR 2025 paper "AMO Sampler: Enhancing Text Rendering with Overshooting"
[NeurIPS 2025 D&B🔥] ImgEdit: A Unified Image Editing Dataset and Benchmark
ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding（书生 · 妙析多模态美学理解大模型）
Ranking LLMs on agentic tasks
This repository contains the Hugging Face Agents Course.
Official implementation of "PyVision: Agentic Vision with Dynamic Tooling."
H-Net: Hierarchical Network with Dynamic Chunking
Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
[NeurIPS' 2025] JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
Official implementation of Inductive Moment Matching
[CVPR 2025] Official repo for ART:Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation
[NeurIPS 2025] 4KAgent: Agentic Any Image to 4K Super-Resolution. An intelligent computer vision agent that can magically restore any image to perfect-4K!
Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)
Dream Recorder is an open-source venture by Modem. Developed in close collaboration with Mark Hinch (software & hardware), Ben Levinas and Joe Tsao (industrial design), and Alexis Jamet (illustrati…
The world's first open-source multimodal creative assistant This is a substitute for Canva and Manus that prioritizes privacy and is usable locally.
Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Models
Official Implementation of Paper Transfer between Modalities with MetaQueries