The Free Software Media System - Server Backend & API

Official implementation of "S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025"

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Sharp Monocular View Synthesis in Less Than a Second

A general fine-tuning kit geared toward image/video/audio diffusion models.

MiniCPM-V 4.5: A GPT-4o Level MLLM for Single Image, Multi Image and High-FPS Video Understanding on Your Phone

Scalable and memory-optimized training of diffusion models

[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

Official implementation of "Depth Any Panoramas: A Foundation Model for Panoramic Depth Estimation".

A pipeline parallel training script for diffusion models.

SkyReels-V2: Infinite-length Film Generative model

Light Image Video Generation Inference Framework

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Official repository for LTX-Video

[SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Wan: Open and Advanced Large-Scale Video Generative Models

央视、卫视和一些地方台、数字台的台标收集，已统一尺寸为 300px*180px，透明底色，命名使用 112114 频道 ID

Official implementation of Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

[NeurIPS 2025] Pixel-Perfect Depth

Official code for the paper: Depth Anything At Any Condition

[CVPR 2025] DEFOM-Stereo: Depth foundation model based stereo matching

[CVPR 2025 Highlight] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos

Official implementation of "DepthMaster: Taming Diffusion Models for Monocular Depth Estimation".

Depth Anything 3

Novel View Synthesis with Pixel-Space Diffusion Models