ModelTC/LightX2V

⚡️ LightX2V:
Light Video Generation Inference Framework

\ English | [中文 \]

--------------------------------------------------------------------------------

LightX2V is an advanced lightweight image/video generation inference framework engineered to deliver efficient, high-performance image/video synthesis solutions. This unified platform integrates multiple state-of-the-art image/video generation techniques, supporting diverse generation tasks including text-to-video (T2V), image-to-video (I2V), text-to-image (T2I), image-editing (I2I). X2V represents the transformation of different input modalities (X, such as text or images) into vision output (Vision).

Quick Start · Models · Documentation & Deployment

🌐 Try it online now! LightX2V Studio is a free, lightweight, and fast AI video generation platform. No installation is required to try MiniMax-H3 / Wan 2.2 / SekoTalk / Qwen-Image / SwiftVR and more.

🍎 MacBook local inference app: LightX2V APP

🤗 HuggingFace Model Repository: LightX2V HuggingFace

🌟 Developer Quick Start: LightX2V Developer Quick Start Guide

📝 Technical Blog: LightX2V Blog

👋 Join our WeChat group! LightX2V Robot WeChat ID: random42seed

🧾 Community Code Contribution Guidelines

Before submitting, please ensure that the code format conforms to the project standard. You can use the following execution command to ensure the consistency of project code format.

pip install ruff pre-commit
pre-commit run --all-files

We thank the following community developers for their contributions to LightX2V:

• zhtshr
• triple-Mu
• vivienfanghuagood
• yeahdongcn

:fire: Latest News

• October 13, 2026: 🎉 We released the LightX2V APP, which supports local inference on MacBook with Qwen-Image-2.1 Turbo, PE-T2I GGUF Q8_0, and PE-I2I GGUF Q8_0 models.
• September 22, 2026: 🚀 We added and optimized support for SwiftVR, covering image and video restoration and super-resolution. See the usage guide.
• September 20, 2026: 🚀 We added day-0 support for Qwen-Image-2.1, covering text-to-image generation and prompt-based image editing. See the usage guide.
• August 27, 2026: 🚀 We released the MiniMax-H3 Turbo 8-step 768p distilled LoRA for generating 768p video with synchronized audio in 8 inference steps using MiniMax-H3. See the MiniMax-H3 guide.
• August 11, 2026: 🚀 We released the MiniMax-H3 Turbo 4-step 768p distilled LoRA and added support for generating 768p video with synchronized audio in 4 inference steps without CFG. See the MiniMax-H3 guide.
• August 7, 2026: 🚀 We added support for synchronized video and audio generation with MiniMax-H3 and released a Prompt Rewriter LoRA that expands short prompts into structured descriptions of visuals, soundscapes, and music. See the MiniMax-H3 guide.

💡 Quick Start

We recommend using LightX2V through its service API. The example below uses MiniMax-H3 for text-to-audio-video (T2AV) generation.

Environment and Model Preparation

We recommend the Docker environment. Clone the repository in your prepared environment:

git clone https://github.com/ModelTC/LightX2V.git
cd LightX2V

Follow the MiniMax-H3 guide to prepare the weights and initial AdaLN cache, check the required kernels, and set the repository path, model path, and GPU in the server script. Run the commands below from the repository root.

pip install -v git+https://github.com/ModelTC/LightX2V.git

uv pip install -v . # or: pip install -v .

Usage Example

# Terminal 1: start the server
bash scripts/minimax_h3/server/start_server.sh

After the model loads, submit the example request from another terminal:

# Terminal 2: submit a T2AV request
python scripts/minimax_h3/server/post_t2av.py

Edit the prompt in the request script to generate your own content. Requests are asynchronous; results are saved by default to save_results/server_cache/outputs/ under the repository root.

🤖 Supported Model Ecosystem

Models and variants are grouped by their primary use.

Video and Audio-Video Generation

• ✅ MiniMax-H3 (including the causal variant)
• ✅ LTX-2 / LTX-2.3 (including the autoregressive variant) / LTX-2.5 (distilled)
• ✅ HunyuanVideo-1.5
• ✅ Wan2.1 / Wan2.2
• ✅ Wan2.1-VACE / Wan2.2-VACE-Fun-A14B
• ✅ Wan2.2-S2V
• ✅ Wan2.2-Animate / Wan2.2-Animate-2 (distilled)
• ✅ LingBot-Video (dense / MoE)
• ✅ SekoTalk (including the autoregressive variant)
• ✅ InfiniteTalk
• ✅ Wan-Dancer
• ✅ Self-Forcing

Image Generation and Editing

• ✅ Qwen-Image / Qwen-Image-2512
• ✅ Qwen-Image-Edit / 2509 / 2511
• ✅ Qwen-Image-2.1 / Turbo
• ✅ Qwen-Image-Layered
• ✅ FLUX.2 dev / klein (including base and distilled variants)
• ✅ HunyuanImage-3.0-Instruct
• ✅ Z-Image / Z-Image-Turbo
• ✅ LongCat-Image / Edit / Edit-Turbo
• ✅ BAGEL
• ✅ HiDream-O1-Image / Dev-2604
• ✅ ERNIE-Image / Turbo
• ✅ SenseNova-U1 (NeoPP backend, used with LightLLM)

Restoration and Super-Resolution

• ✅ SeedVR2
• ✅ SwiftVR

World Models, Robotics, and 3D

• ✅ Cosmos3-Nano / Super (including Nano-Policy-DROID)
• ✅ LingBot-World / Fast
• ✅ Matrix-Game-2.0 / 3.0
• ✅ WorldPlay (bidirectional, autoregressive, and distilled)
• ✅ WorldMirror 2.0 (3D reconstruction)
• ✅ DreamZero
• ✅ LingBot-VA
• ✅ Motus
• ✅ Fast-WAM
• ✅ RealtimeWAM (based on Fast-WAM / Faster-WAM)
• ✅ Hunyuan3D-2.1 (image-to-3D shape generation)

Quantized and Distilled Models/LoRAs

• ✅ MiniMax-H3 Turbo — 4-/8-step 768p distilled LoRAs for T2AV / FL2AV
• ✅ LightLingBot-Video — 4-step distilled LoRA for T2V, T2I, and I2V
• ✅ Wan2.1-Distill-Models / Wan2.2-Distill-Models
• ✅ Wan2.1-Distill-Loras / Wan2.2-Distill-Loras
• ✅ Wan-NVFP4 / LightWan2.2-A14B
• ✅ Hy1.5-Distill-Models / Hy1.5-Quantized-Models
• ✅ Qwen-Image-Lightning / Qwen-Image-2512-Lightning / Qwen-Image-2.1-Lightning
• ✅ Qwen-Image-Edit-2511-Lightning
• ✅ Z-Image-Turbo-Quantized
• ✅ Self-Forcing-FP8 / Self-Forcing-NVFP4

Lightweight Autoencoders

• ✅ Autoencoders (LightVAE / LightTAE)

🚀 Core Features

• Few-Step Inference: Support distilled checkpoints and distillation LoRAs, including DMD2 and Wan2.1 MeanFlow inference.
• Quantization & Optimized Kernels: Support W8A8 (INT8 / FP8) and W4A4 (NVFP4) quantization, with optimized attention backends such as FlashAttention and SageAttention.
• Hierarchical Offloading: Manage weights across disk, CPU, and GPU with model-level and block-level offloading.
• Feature Caching: Support TeaCache, MagCache, and TaylorSeer to reuse intermediate results across denoising steps.
• Parallel Inference: Support tensor parallelism (TP), sequence parallelism (SP), CFG parallelism, and hybrid configurations.
• Variable-Resolution Inference: Schedule latent resolutions across denoising stages to control computation at each stage.

📚 Documentation & Deployment

| Use Case | Documentation & Examples | | --- | --- | | Environment Setup & Configuration | Quick Start Guide | | Model Preparation & Loading | MiniMax-H3 · Wan2.1 / VACE · Model Formats & Loading | | Service Deployment & API Usage | Service Deployment · API Reference | | Interactive Interfaces & Workflow Integration | Gradio-Lightx2v · ComfyUI | | Local Deployment on Windows | Windows Deployment Guide | | Resource-Constrained and Low-Latency Deployment | Low-Resource Deployment · Low-Latency Deployment | | Model Quantization & LoRA Deployment | Quantization · LoRA Deployment | | Inference Performance Optimization | Weight Offloading · Feature Caching · Attention Kernels · Parallel Inference · Variable-Resolution Inference · Step Distillation | | Wan2.1 NVFP4 4-Step Inference | I2V Example · T2V Example · [Quantization Kernel Installation](lightx2v_kerne