{
  "schemaVersion": "1",
  "revision": "22ce5d34dbcb5a78",
  "id": "factory-tools-image-generation-variations",
  "slug": "tools-image-generation-variations",
  "title": "Image generation for design variations",
  "summary": "Tool roles, alternatives, selection tradeoffs, and compatibility caveats.",
  "category": "Tools",
  "tags": [
    "tools",
    "image-generation-variations"
  ],
  "sources": [
    {
      "label": "Tool comparison reference",
      "url": "https://dewy-sleet-n5zs.here.now/#image-generation-variations"
    }
  ],
  "sourceUnits": [
    "resources/index.html#image-generation-variations"
  ],
  "collection": "factory",
  "categoryId": "tools",
  "wordCount": 302,
  "url": "/topics/factory-tools-image-generation-variations/",
  "markdownUrl": "/markdown/factory-tools-image-generation-variations.md?raw=1&v=22ce5d34dbcb5a78",
  "jsonUrl": "/api/v1/documents/factory-tools-image-generation-variations.json",
  "headings": [
    {
      "id": "image-generation-for-design-variations",
      "text": "Image generation for design variations",
      "level": 2
    },
    {
      "id": "pick-this-if",
      "text": "Pick this if…",
      "level": 3
    }
  ],
  "markdown": "# Image generation for design variations\n\nTool roles, alternatives, selection tradeoffs, and compatibility caveats.\n\n## Image generation for design variations\n\n**John uses:** Codex's built-in **\\$imagegen** skill (GPT image model, no API key beyond the Codex subscription) and **agy** — the [Antigravity CLI](https://github.com/google-antigravity/antigravity-cli) (1.6k) with Gemini's `generate_image` — to produce 9 wildly different mockups per prompt, then hands the winner to a coding agent as a reference image (section 07).\n\n| Alternative | What it is | How it differs | License |\n|----|----|----|----|\n| [Gemini CLI](https://github.com/google-gemini/gemini-cli) | Google's terminal agent; image generation via Gemini/Imagen models on the free tier | Same Google image models as agy without the Antigravity harness | Apache-2.0 |\n| [ComfyUI](https://github.com/Comfy-Org/ComfyUI) | Node-graph GUI/API/backend for diffusion models, fully local | Local + free at inference; scriptable API makes 9x batch generation easy; needs a GPU and setup | GPL-3.0 |\n| [mflux](https://github.com/filipstrand/mflux) | MLX-native FLUX and other image models on Apple Silicon | Runs the 9x pattern locally on the same Mac you present from; CLI-first | MIT |\n| [InvokeAI](https://github.com/invoke-ai/InvokeAI) | Professional creative engine/WebUI for Stable Diffusion family models | Polished local UI aimed at designers rather than agent scripting | Apache-2.0 |\n| [AUTOMATIC1111 stable-diffusion-webui](https://github.com/AUTOMATIC1111/stable-diffusion-webui) | The historically dominant SD web UI | Huge ecosystem but slowing maintenance (check repository activity before adoption); prefer ComfyUI/Invoke for new setups | AGPL-3.0 |\n\n### Pick this if…\n\n- **Gemini CLI** — you want the agy pattern without Antigravity, free.\n- **ComfyUI** — you want local, free-at-inference batch generation with a scriptable API (needs GPU).\n- **mflux** — you present from a Mac and want the 9x loop fully local on Apple Silicon.\n- **InvokeAI** — you want a designer-friendly local UI over raw pipelines.\n- **A1111** — only if you need its ecosystem; prefer ComfyUI/Invoke for new setups."
}
