# ModelTC/LightX2V

Lightweight Image Video Action Generation Inference Framework

Repository: https://github.com/ModelTC/LightX2V
Canonical: https://ross.abutalabs.com/products/lightx2v
Homepage: https://x2v.light-ai.top/generate
Language: Python
License: Apache-2.0
License Family: permissive
Topics: video-generation, wan-video, diffusion-models, auto-regressive-diffusion-model, world-models, qwen-image, ltx-video, hunyuan-video, dreamzero, lingbot-world
Last push: 2026-08-26T11:24:43+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 37
- inputs: {"age_days": 527, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2733, forks 260 (observed 2026-08-28T04:07:16.073901+00:00)

## What it is
LightX2V is a lightweight, high-performance inference framework for image and video generation, supporting tasks like text-to-video, image-to-video, text-to-image, and image editing with models such as Wan, Hunyuan, LTX, and Qwen-Image. It provides end-to-end acceleration, an online studio, OpenAPI, and agent skills for AI video, image, and audio creation.

## Use cases
- generate videos from text prompts
- animate a still image into a video
- run wan video model inference faster
- generate images from text
- create digital human avatar videos
- do motion transfer and character replacement
- upscale and restore video quality
- serve video generation behind an api

## When to choose
- you need efficient inference for diffusion-based video generation models like Wan, Hunyuan, or LTX
- you want a unified framework covering text-to-video, image-to-video, and image editing
- you need GPU-accelerated, production-ready video generation with an API or web studio
- you want to run generation on limited hardware thanks to lightweight optimizations

## When to avoid
- you need to train or fine-tune video diffusion models from scratch rather than run inference
- you need a general-purpose video editing suite rather than AI generation
- your project requires models outside the supported Wan/Hunyuan/LTX/Qwen ecosystem

## Facets
- artifact type: framework
- maturity: active
- function: llm-inference, image-processing, video-processing, machine-learning, deep-learning, gpu-computing
- domain: artificial-intelligence, deep-learning, image-processing, media, developer-tools
- platform: python, cross-platform
- tags: video-generation, diffusion-models, text-to-video, image-to-video, text-to-image, wan-video, hunyuan-video, ltx-video, qwen-image, inference-optimization, digital-human, tts, video, linux, gpu, docker, web-server

## Member repositories
- ModelTC/LightX2V (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:16.073901+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:14:29.346313+00:00, confidence not recorded.
  - readme: https://github.com/ModelTC/LightX2V (fetched 2026-08-28T04:07:16.073901+00:00, sha f42701b0776d)
  - homepage: https://x2v.light-ai.top/generate (fetched 2026-08-29T09:57:42.829071+00:00, sha bba47ebcfce5)
  - site_page: https://x2v.light-ai.top/api-docs (fetched 2026-08-29T09:57:42.838742+00:00, sha a4c846c7bbbe)
  - site_page: https://x2v.light-ai.top/en/api-docs (fetched 2026-08-29T09:57:42.840654+00:00, sha 12c4bb811358)
- Data as of 2026-08-30T08:39:29.467469+00:00.