An OpenClaw skill for the LightX2V cloud API that covers text-to-image, image editing, text-to-video, image-to-video, first-last-frame video, talking-head video, TTS and voice cloning. The hosted models include Wan 2.2 for video and Qwen-Image for images, and the free tier allows 100 task submissions a day with your own access token. Install with the repo's install.sh, which copies the skill into your OpenClaw workspace.
INSTALL X2V-AI-IMAGES-VIDEOS-SKILL
git clone https://github.com/xinyiqin/X2V-AI-Images-Videos-skill.git
The README has no one-line installer. Clone the repo, then follow its README to install.
STACK
OpenClawLightX2VWan 2.2Shell
“[LightX2V](https://x2v.light-ai.top) integration for [OpenClaw](https://openclaw.ai) — image generation (t2i/i2i), video (t2v/i2v/s2v), TTS, and voice clone via cloud API.”
About Avatars
Digital presenters: talking heads, lip-sync and virtual hosts.