Ima2 Gen

Generate, branch and clean up images and video on your own machine. One local studio for GPT, Grok, Gemini, NovelAI and ComfyUI. Use it from the browser, the Mac app, the CLI, or hand it to your coding agent.

npm install -g ima2-gen
ima2 serve

Create

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.

Branch in Node graph

Keep a good image and push it in several directions at once. Each branch remembers its parent, so nothing gets overwritten.

Clean up in Canvas Mode

Annotate, erase, cut backgrounds and export with real alpha. One-click GPT transparency is checked on the server before the app calls it transparent.

Start from Home

See which lanes are ready, type a prompt, and pick up recent work without digging through folders.

English · 한국어 · 日本語 · 简体中文 · 正體中文 · Website · Docs →

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.

Quick start

Mac app (Apple Silicon)

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.

1. Download ima2-<version>-mac-arm64.dmg from the newest ima2 Desktop release.
2. Open the DMG and drag ima2 into Applications.
3. Launch ima2 and pick a provider on the welcome screen.

The Mac App guide covers checksums, updates and settings. On an Intel Mac, Windows or Linux, use npm or a one-line installer.

npm

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.

First image from the CLI

Pick explicit image and video defaults once, then generate:

ima2 models
ima2 defaults set image oauth/gpt-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.

One-line installers (no npm required)