agentsclimarketplace
Sign in

Lightx2v ai video generation

Skill ModelTC/LightX2V-Skills/.agents/skills/lightx2v-ai-video-generation

Run LightX2V AI generation tasks from the command line via OpenAPI. Commands: lightx2v login, models, run, query, list, cancel, resume, delete, result, completion. Tasks: t2i, t2v, i2v, s2v, flf2v, t2av, i2av, vsr, animate, i2i. Use for: scriptable video/image generation, CI pipelines, agent automation, batch jobs. Triggers: lightx2v cli, lightx2v run, api key generation, text to video cli, text to image cli, download generated video, poll task statusFrom its SKILL.md

Install
npx -y skills add ModelTC/LightX2V-Skills --skill lightx2v-ai-video-generation

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.7 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

Install skill: npx skills add ModelTC/LightX2V-Skills@lightx2v-ai-video-generation

Install CLI: curl -fsSL https://raw.githubusercontent.com/ModelTC/lightx2v-studio-cli/main/install.sh | sh

Skills directory: https://skills.sh/ModelTC/LightX2V-Skills

LightX2V AI Video Generation

Submit and download AI generation tasks via the LightX2V OpenAPI.

Online API docs: https://x2v.light-ai.top/api-docs

Quick Start

curl -fsSL https://raw.githubusercontent.com/ModelTC/lightx2v-studio-cli/main/install.sh | sh
lightx2v login
lightx2v models
lightx2v run t2i/Qwen-Image-2512 --prompt "a cute cat" --shape 512,512 -o out.png

Commands

CommandDescription
lightx2v login [--base-url URL]Save apikey_ to ~/.config/lightx2v/config.json
lightx2v models [--json]List task/model combinations
lightx2v run <task>/<model_cls> ...Submit, poll, download (main workflow)
lightx2v query <task_id> [--json]Query single task
lightx2v list [--status] [--page]Paginated task list
lightx2v cancel <task_id>Cancel running task
lightx2v resume <task_id>Resume failed/cancelled task
lightx2v delete <task_id>Delete finished task
lightx2v result <task_id> [-o PATH]Get result URL / download
lightx2v completion bash or zshShell completion script

run options

FlagDescription
--promptPrompt text
--input JSON or --input @file.jsonExtra submit body fields
--image / --video / --audioLocal file to base64 input
--shape H,Wcustom_shape e.g. 720,1280
--aspect-ratioe.g. 16:9
--duration SECSeconds (t2av/i2av/s2v)
--vsr-preset / --vsr-input-slotVSR options
-o PATHOutput file
--quotePre-submit billing quote
--jsonStructured JSON event stream
-q / --quietMinimal output
--no-downloadReturn URL only

Examples

Text-to-image

lightx2v run t2i/Qwen-Image-2512 --prompt "watercolor portrait" --aspect-ratio 16:9 -o portrait.png

Text-to-video

lightx2v run t2v/Wan2.2_T2V_A14B_distilled --prompt "waves at sunset" --shape 720,1280 -o beach.mp4

Image-to-video

lightx2v run i2v/Wan2.2_I2V_A14B_distilled --prompt "subject turns and smiles" --image ./ref.png -o animated.mp4

Digital human (s2v)

lightx2v run s2v/SekoTalk --prompt "natural speaking" --image ./portrait.png --audio ./speech.wav -o avatar.mp4

Task management

lightx2v query TASK_ID
lightx2v list --status SUCCEED --page 1 --page-size 20
lightx2v cancel TASK_ID
lightx2v result TASK_ID -o output.png

Notes

  • API channel costs 2x web UI credits; run prints quoted_credits.
  • Config: ~/.config/lightx2v/config.json (mode 0600).
  • Env: LIGHTX2V_API_KEY, LIGHTX2V_CLOUD_API_KEY, LIGHTX2V_BASE_URL.
  • Large media: prefer url in --input JSON over base64.

Related

What ships with it: 2 files

16.9 KB alongside SKILL.md

references/

Keep looking

Skills are one crate of 326,149. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.