ima2-gen
A local-first visual generation runtime and studio for people and coding agents, with reproducible image and video workflows across multiple providers.
Verified
Core facts
Read by a script from the official API, not rewritten by a model.
- Repository
- https://github.com/lidge-ai/ima2-gen
- License
- MIT
- Languages
- TypeScript
- Maintainer
- lidge-ai
- Verified
What it is
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. Prompts and references go only to the provider you pick for each job. Runway and Higgsfield stay separate MCP-backed integrations.
Main features
In Create, you can attach up to 5 references for images or up to 14 for video, and large images are compressed before upload.
In the Node graph, root nodes take local references and child nodes use their parent image as the source.
Raster to vector traces flat raster art into real SVG paths with the vectorize command, from AssetGen/Assets, or from Canvas Export.
The prompt library imports local prompt packs, GitHub folders and curated GPT-image hints, and imports are indexed locally for search; Prompt Builder refines intent through a text backend.
ima2-gen ships three Markdown skills that coding agents load for structured image, video, frontend-asset and design-direction workflows, and in the local gallery every image and video stays on your machine with session-aware history, generation time and reasoning effort in its metadata.
Getting started
The desktop app runs the same local server and studio in a Mac window with a menu bar icon.
On an Intel Mac, Windows or Linux, use npm or a one-line installer.
In the Mac app, launch ima2 and pick a provider on the welcome screen.
ima2 setup offers four authentication choices.
Each one-line installer 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 the server.
For the first image from the CLI, pick explicit image and video defaults once, then generate.
npm install -g ima2-gen
ima2 setup
ima2 serveima2 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 720pcurl -fsSL https://ima2gen.com/install-mac.sh | bashirm https://ima2gen.com/install-windows.ps1 | iexcurl -fsSL https://ima2gen.com/install-linux.sh | bashWho it is for
The Mac app brings its own runtime, so it does not need Node.js. Only the macOS desktop app for Apple Silicon is distributed today. The one-line installer script does not stop unrelated processes or clear global locks.
Card News exists as a dev-only experiment and is hidden in the published runtime. The GPT OAuth lane offers three GPT-6 models. On that lane, the chosen model plans the image and gpt-image-2 draws it.
Related tools
Related tools listed on this site.
EveryGen AI
Video generator and creative studio describing scene planning, clips, image editing, voices, music and video assembly.
QwenPaw
Personal AI assistant and agent workstation running in your own environment. Its primary description presents local/cloud deployment, multiple channels and extension through Skills and MCP.
Cursor
A coding agent for understanding repositories, planning features, changing code, and reviewing diffs.
CodeBuddy IDE
AI coding workspace for product, design and development. Its dedicated IDE documentation describes technical conversations, code completion, Figma-to-code, diagnostics and a design-to-deployment workflow.
InfCode
Enterprise AI coding agent from TokensInfinity. Its site describes using enterprise code and knowledge through IDE, extension and CLI forms for completion, cross-file changes and engineering tasks.
阿里云百炼
Alibaba Cloud Bailian is a model-service and application-development platform for model inference, knowledge bases, agents and workflows.
千问云
The discovered Qianwen Cloud entry currently presents the Qianwen AI Platform for model discovery, online trials, API access, Skills/CLI tooling and usage/cost management.
Figma AI
Collection of AI workflows and capabilities within Figma products for design exploration, content editing and connecting prototypes with code.
Pixso AI
AI design capability integrated into the Pixso canvas. Its official page describes generating editable web and mobile interfaces from text, sketches or screenshots and continuing to refine existing designs.
Ardot
AI design and collaboration tool. Its official site describes text/image-to-editable UI, vector editing, dynamic layouts and design systems, plus collaboration, annotations and design-to-development handoff.
纳米AI
Nano AI is an AI search and agent assistant whose site says it can generate videos, reports and slides from one sentence and integrates several large models.
Exa AI
Exa is a web-retrieval service for AI applications and agents, describing search, content retrieval, deep research and structured-output APIs.
Related guides
- skill-creator: Anthropic's skill for writing, editing and evaluating skillsAnthropic's skill-creator skill: draft a skill, run evals, revise it and tune its trigger description. Not tested here; follow the official text and docs.
- webapp-testing Skill: drive local web apps with PlaywrightOfficial Anthropic webapp-testing Skill: Python Playwright scripts for local web apps, not tested
- frontend-design: avoiding templated defaults in UI designAnthropic's frontend-design skill: plan the visual direction, check it against the brief, avoid templated defaults. Not tested; follow the official text.
- gh-address-comments: work through GitHub PR review commentsOfficial OpenAI Codex skill: fetch comments on the current branch's PR with the gh CLI, number them, then fix only the ones you pick; not tested.
- security-best-practices: language- and framework-specific security reviewOfficial OpenAI Codex skill: load security references matching the project's language and framework, then write safer code or a report; not tested.
Sources
This page is written from the official sources below. Open them to check the original text.
- GitHub READMEhttps://github.com/lidge-ai/ima2-genFetched
Verified ·
This page is written by AI from the official sources above and checked automatically. This site has not tested it. Found a mistake? Tell us.