by lidge-ai
Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.
# Add to your Claude Code skills
git clone https://github.com/lidge-ai/ima2-genLast scanned: 9/25/2026
{
"issues": [
{
"type": "npm-audit",
"message": "@ai-sdk/gateway: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "@ai-sdk/provider-utils: @ai-sdk/provider-utils has an Uncontrolled Resource Consumption issue",
"severity": "low"
},
{
"type": "npm-audit",
"message": "ai: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "hono: Hono: Incomplete fix for CVE-2026-39408: `toSSG()` still writes files outside the output directory",
"severity": "medium"
},
{
"type": "npm-audit",
"message": "openai-oauth: Vulnerability found",
"severity": "low"
},
{
"type": "npm-audit",
"message": "qs: qs array-limit bypass via bracket-key comma parsing",
"severity": "medium"
},
{
"file": "README.md",
"line": 247,
"type": "secret-exfiltration",
"message": "Instruction appears to send credentials/secrets to an external endpoint",
"severity": "medium"
},
{
"file": "README.md",
"line": 129,
"type": "remote-install",
"message": "Install command (remote install script piped to a shell — review the source before running): \"curl -fsSL https://lidge-jun.github.io/ima2-gen/install-mac.sh | bash\"",
"severity": "low"
}
],
"status": "PASSED",
"scannedAt": "2026-09-25T09:25:10.375Z",
"npmAuditRan": true,
"pipAuditRan": true,
"promptInjectionRan": true
}See how ima2-gen compares with popular alternatives.
ima2-gen is an open-source ai agents skill for AI coding assistants such as Claude Code, Codex CLI, and ChatGPT, built by lidge-ai. Local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers. It has 785 GitHub stars.
Yes. ima2-gen passed SkillsLLM's automated security scan — a dependency vulnerability audit plus prompt-injection heuristics — with no high-severity issues. You can read the full report in the Security Report section on this page.
Clone the repository with "git clone https://github.com/lidge-ai/ima2-gen" and add it to your Claude Code skills directory (see the Installation section above).
ima2-gen is primarily written in TypeScript. It is open-source under lidge-ai on GitHub, so you can review or fork the full source.
Yes. SkillsLLM lists many other AI Agents skills you can browse and compare side by side. Open the AI Agents category from the badge at the top of this page, or use the Related Skills and comparison links further down to weigh ima2-gen against similar tools.
No comments yet. Be the first to share your thoughts!
⚠️ Third-Party Software Notice
This skill is third-party open-source software developed and hosted independently on GitHub. SkillsLLM is an informational directory and does not control or maintain the underlying repository.
Any security checks, ratings, or warnings displayed by SkillsLLM are automated and limited in scope. They do not constitute a security certification or guarantee that the software is safe, error-free, or free from malicious code, vulnerabilities, compromised dependencies, or prompt-injection risks.
Review the source code, permissions, dependencies, and configuration before installing or running any third-party skill. Use is at your own risk. To the maximum extent permitted by applicable law, SkillsLLM is not liable for losses arising from third-party software.
npm install -g ima2-gen
ima2 serve
Write a prompt, attach references, pick a lane and model. Every result keeps its prompt, timing and settings, so you can copy it, continue from it, or animate it.
Keep a good image and push it in several directions at once. Each branch remembers its parent, so nothing gets overwritten.
Annotate, erase, cut backgrounds and export with real alpha. One-click GPT transparency is checked on the server before the app calls it transparent.
See which lanes are ready, type a prompt, and pick up recent work without digging through folders.
ima2-gen is a local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers. It runs a small server on your machine, keeps every image in ~/.ima2/generated, and talks to the providers you connect: OpenAI OAuth/API, Grok OAuth/API, Antigravity CLI, Gemini API, AtlasCloud, MiniMax, NovelAI and registered ComfyUI workflows. Runway and Higgsfield stay separate MCP-backed integrations. Prompts and references go only to the provider you pick for each job.
The desktop app runs the same local server and studio in a Mac window with a menu bar icon. It is signed with a Developer ID and notarized by Apple, and it brings its own runtime, so you do not need Node.js.
ima2-<version>-mac-arm64.dmg from the newest ima2 Desktop release.The Mac App guide covers checksums, updates and settings. On an Intel Mac, Windows or Linux, use npm or a one-line installer.
npm install -g ima2-gen
ima2 setup
ima2 serve
Then open http://localhost:3333. If 3333 is taken, ima2-gen binds the next free port and writes the real URL to ~/.ima2/server.json; ima2 open always finds it.
Pick explicit image and video defaults once, then generate:
ima2 models
ima2 defaults set image oauth/gpt-5.6-luna
ima2 defaults set video grok/grok-imagine-video-1.5
ima2 gen "a clean product photo of a red guitar pedal"
ima2 video "a cat playing piano" --duration 5 --resolution 720p
ima2 gen and generate-mode ima2 video fail closed with NO_DEFAULT_MODEL until a CLI target is configured, unless the call passes --model <lane>/<model> or an explicit --provider <lane>. An upgrade can never silently switch providers or billing lanes.
Each script checks the package-derived Node.js floor, installs Node LTS if needed, installs ima2-gen once, and runs the offline installation check before launching ima2 serve. It does not stop unrelated processes or clear global locks.
macOS
curl -fsSL https://lidge-jun.github.io/ima2-gen/install-mac.sh | bash
Windows (PowerShell)
irm https://lidge-jun.github.io/ima2-gen/install-windows.ps1 | iex
Linux / WSL
curl -fsSL https://lidge-jun.github.io/ima2-gen/install-linux.sh | bash
docker build -t ima2-gen .
docker run -d -p 3333:3333 -e IMA2_LAN_TOKEN=change-me -v ima2-data:/data ima2-gen
See docs/DOCKER.md for compose usage, required environment, and limitations.
ima2 setup offers four authentication choices:
Video generation needs Grok OAuth (option 2 or 3). If you already use GPT OAuth, run ima2 grok login to add video; it defaults to the manual-paste flow.
To update, stop the server with Ctrl+C (or ima2 stop from another terminal), then run:
npm install -g ima2-gen@latest
Ctrl+C shuts down cleanly: it closes the database, stops child processes and releases file locks. If an install fails, check the reported npm permissions or stop the specific ima2 process yourself; the installer does not perform broad process cleanup.
Using npx instead? See docs/NPX_QUICKSTART.md for the npx ima2-gen serve workflow.
alphaVerified from the decoded bytes. Saved canvas versions stay out of Gallery and the history strip, but Canvas Mode can reopen them and attach one as the next reference.ima2 vectorize, from AssetGen/Assets, or from Canvas Export.