Repository Index

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

• cuda
• inference
• llama
• llm

Official repository for LTX-Video

• diffusion-models
• dit
• image-to-video
• image-to-video-generation

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

• generative-ai
• ltx
• ltx-2

Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

• lip-sync
• virtualhumans

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

• image-to-video
• text-to-video
• video-generation

[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

• editing
• video

A Tensorflow implementation of AnimeGAN for fast photo animation ! This is the Open source of the paper 「AnimeGAN: a novel lightweight GAN for photo animation」, which uses the GAN framwork to transform real-world photos into anime images.

• photo-animation
• animegan
• hayao-style
• tensorflow

HunyuanVideo-1.5: A leading lightweight video generation model

• image-to-video
• text-to-video
• video-generation

[AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

• audio-driven-talking-face
• talking-head
• audio-driven-portrait-animations
• talking-face-generation

[ICLR 2025] Hallo2: Long-Duration and High-Resolution Audio-driven Portrait Image Animation

[SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer

• face
• siggraph-asia
• style-transfer
• stylegan2

TranslatedHigh-performance · Lightweight · AI Native Video workspace. A video creation workspace for the AI era. On the canvas, freely connect ideas and materials together with the Agent.

• ai-image-generation
• ai-video
• ai-video-generation
• ai-workspace

One-click character swap for videos: an open-source, local Higgsfield Genjutsu alternative built on ComfyUI and MiniMax H3, with FLUX.3 Klein relighting.

• character-swap
• comfyui
• minimax-h3
• nextjs

We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.

• diffusion-models
• high-resolution
• sparse-attention
• video-generation

TranslatedA skill for making Douyin hit "Vibe knowledge showcase" educational short films: deeply breaks down viral videos, replicates the art style, produces a director's storyboard table, adds sound effects automatically, and outputs the finished video in one click

• agent-skills
• ai-video
• claude-code
• claude-skills

Open-source Higgsfield on ComfyUI: 120 image, video, VFX and audio apps, every model open weights; runs on Modal or your own GPU

• comfyui
• higgsfield
• image-generation
• ltx-video

[WACV 2027] ComplexSync: High-Fidelity and Real-Time Lip Sync in Complex Scenarios

Open-source studio for video, stills and 3D on your own GPU through ComfyUI