HN Showcase
Back to browse
GitHub Repository
3 starsTypeScript

CLI Image Generation Agent Using (OpenRouter and Free Models)

by Kiran7893·Feb 21, 2026·2 points·0 comments
Visit ProjectView on HN

AI Analysis

●MidShip It

Free-tier image agent, but prompt expansion and routing aren't novel vs Comfy UI or ComfyUI agents.

Strengths
  • •Pragmatic demo of free AI model stacking (OpenRouter, free tiers) with modular subagent pattern.
  • •React Ink CLI UX is respectable; automatic prompt refinement shows intent-based routing thinking.
Weaknesses
  • •Core idea (expand prompt → route → generate) is solved by ComfyUI, Midjourney prompt refinement, and dozens of image agent repos.
  • •No differentiation: same free models everyone else uses, no fine-tuning, no unique routing logic.
Category
AI/ML
Target Audience

Artists, developers experimenting with image generation, users wanting free API alternatives to paid services.

Similar To

ComfyUI · Midjourney · Replicate CLI agents

Post Description

built a CLI-based image generation agent that takes vague prompts like: “a warrior in a forest” And automatically: Expands it into a detailed cinematic description (lighting, mood, camera angle, art style) Routes it to the appropriate model via OpenRouter Downloads the generated image locally

Tech stack: React Ink (CLI UI) TypeScript Modular subagent architecture OpenRouter (free-tier models supported) One thing I realized while building this: You don’t actually need expensive API credits to experiment with AI agents.

There’s a surprisingly strong free stack available: OpenRouter (multiple free-tier models) Antigravity (Claude, GPT variants, Gemini access) OpenCode (GLM-5, MiniMax) Local models via LM Studio / Ollama / ComfyUI

The biggest barrier isn’t cost — it’s clarity of architecture.

Repo: https://github.com/kiran7893/Image-generation-agent

Similar Projects