image-to-video · eachlabs — Claude Code skill: what it does, how to install
Turns still photos into short videos with each::sense: subtle motion, cinemagraphs, camera pushes. Handy when all you have is one image.
npx skills add eachlabs/skills --skill image-to-video -a claude-codeWhat image-to-video does
This skill lets the agent build a short video from a single still image via each::sense. It covers gentle photo motion, slow pan-and-zoom moves, cinemagraphs where only one area loops, parallax depth and animated logo intros. Portraits and landscapes get their own prompt examples.
What ships is a set of ready curl calls to the each::sense API, with no local code. The image goes in as a link under image_urls, and your EACHLABS_API_KEY travels in the X-API-Key header. No key, no video.
The text of the request decides what moves and what stays frozen. For a cinemagraph, name the one detail that should live, like steam over a cup.
What it helps with
- animate a portrait with breathing and small eye movements
- push the camera slowly toward the subject of a landscape
- loop one detail of a frame while the rest stays still
- build a product clip with a camera orbit from one photo
- turn a flat logo into a video intro
Example prompts for the agent
- Use image-to-video on
photo.jpgand give it gentle, natural movement - Make a cinemagraph from the coffee shop picture where only the steam moves
- Apply a slow documentary-style zoom into the centre of this landscape
How to install image-to-video
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill image-to-video -a claude-code2Manually: put the files in place
~/.claude/skills/image-to-video/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/image-to-video/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill image-to-video -a codex2Manually: put the files in place
.agents/skills/image-to-video/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill image-to-video -a cursor2Manually: put the files in place
.cursor/skills/image-to-video/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install eachlabs/skills image-to-video2Manually: put the files in place
.github/skills/image-to-video/SKILL.md1Skills CLI (Vercel)
npx skills add eachlabs/skills --skill image-to-video -a gemini-cli2Platform CLI
gemini skills install https://github.com/eachlabs/skills --path skills/image-to-videoManually: put the files in place
.devin/skills/image-to-video/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add eachlabs/skills --skill image-to-video -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about image-to-video
How do I install image-to-video in Claude Code?
Run npx skills add eachlabs/skills --skill image-to-video -a claude-code. The skill file lands at ~/.claude/skills/image-to-video/SKILL.md.
What does image-to-video do?
It sends an image plus a text description of the motion to each::sense and gets a video back: photo animation, cinemagraph, camera push, parallax or logo animation.
What do I need before using image-to-video?
An EACHLABS_API_KEY for the X-API-Key header and a link to the source image, passed as image_urls. The skill installs into Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and OpenCode.
Similar skills
All skills for AI and ML →image-to-video by other authors comes first.
