Repository for the CVPR 2026 paper MeshFlow Efficient Artistic Mesh Generation via MeshVAE and Flow-based Diffusion Transformer by Weiyu Li, Antoine Toisoul, Tom Monnier, Roman Shapovalov, Rakesh R…

[CVPR 2026 Findings] TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis

A niche toolkit for computer vision and more.

🌍 WorldGen - Generate Any 3D Scene in Seconds

"Single-image Layer Decomposition for Anime Characters" (SIGGRAPH 2026 Conference Paper)

SGLang is a high-performance serving framework for large language models and multimodal models.

Code for RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion [3DV 2025]

Research on Coding Agents

A collection of awesome video generation studies.

Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1

AI agents running research on single-GPU nanochat training automatically

Helios: Real Real-Time Long Video Generation Model

[CVPR 2026] WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories (WorldExpand of HY-World 2.0)

GPU Engineering for AI Systems

[ICCV 2023] Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising && [Arxiv 2023] Make Explicit Calibration Implicit: Calibrate Denoiser Instead of the Noise Model && …

Official code repository for the paper A Large-scale AI-generated Image Inpainting Benchmark

Machine Learning Journal for Intermediate to Advanced Topics.

AI video production in the browser — text-to-video, image-to-video, lip sync, 100+ models. Google Veo 3.1, FLUX, Gemini, Imagen 4. Free, open-source, private.

Workflow ComfyUI to upscale and magnify video using comfyui - based on cseti007 workflows

LiteRT, successor to TensorFlow Lite. is Google's On-device framework for high-performance ML & GenAI deployment on edge platforms, via efficient conversion, runtime, and optimization

[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

[CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control

诺亚盘古大模型研发背后的真正的心酸与黑暗的故事。

[ACM MM 2025] FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis

PixelHacker: Image Inpainting with Structural and Semantic Consistency

Virtual whiteboard for sketching hand-drawn like diagrams

SkyReels-V2: Infinite-length Film Generative model

[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation