\r \r

Image Generation\r

\r Use this skill when you need to create one or more image files from a text prompt, or edit one or more existing images with Gemini.\r \r

Requirements\r

\r \r

• ~/.openclaw/openclaw.json must include $.skills.entries["gemini-image-generation"].enabled set to true.\r
• ~/.openclaw/openclaw.json must include $.skills.entries["gemini-image-generation"].env with the following keys and values:\r
• GEMINI_API_KEY required\r
• GEMINI_MODEL_ID required\r
• GEMINI_BASE_URL optional\r \r
• example ~/.openclaw/openclaw.json:\r

{\r
  ......,\r
  "skills": {\r
    "entries": {\r
      "gemini-image-generation": {\r
        "enabled": true,\r
        "env": {\r
          "GEMINI_API_KEY": "sk-xxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx",\r
          "GEMINI_MODEL_ID": "gemini-3.1-flash-image-preview",\r
          "GEMINI_BASE_URL": "https://custom-endpoint.com"\r
        }\r
      }\r
    }\r
  },\r
  ......\r
}\r
```\r
- Node.js must be installed in the workspace environment.\r
- Install dependencies once with `npm install` from the skill root.\r
\r
## When To Use\r
\r
- The user asks to generate a new image from a text prompt.\r
- The user asks to modify, restyle, extend, or otherwise edit one or more existing images.\r
- The user wants the generated image saved to a workspace file.\r
- The task should be handled through a reusable OpenClaw skill instead of ad hoc SDK code.\r
\r
## Procedure\r
\r
1. Convert the user request into a single clear image prompt.\r
2. If the user supplied source images, choose or confirm the input file path or paths inside the workspace.\r
3. If the user specified a target aspect ratio or size, pass them through as `--aspectRatio` and `--imageSize`.\r
4. Choose an output path inside the workspace unless the user already provided one.\r
5. For text-to-image, run [generate-image.mjs](./scripts/generate-image.mjs) with `--prompt`, `--output`, and optional image config arguments.\r
6. For image editing, run [edit-image.mjs](./scripts/edit-image.mjs) with `--prompt`, one or more `--input` values, `--output`, and optional image config arguments.\r
7. Read the api key from `GEMINI_API_KEY` and the model ID from `GEMINI_MODEL_ID` in the environment.\r
8. Optionally, read the base URL from `GEMINI_BASE_URL` in the environment for custom endpoints.\r
9. Return the saved image path or paths to the user.\r
10. After returning each image path, also output `MEDIA:\x3Cimage_path>` (e.g. `MEDIA:outputs/gemini-native-image.png`) so the image is displayed inline in the conversation.\r
\r
## Commands\r
\r
```powershell\r
node ./skills/gemini-image-generation/scripts/generate-image.mjs --prompt "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme" --output "outputs/gemini-native-image.png"\r
```\r
\r
```powershell\r
node ./skills/gemini-image-generation/scripts/generate-image.mjs --prompt "Create a wide cinematic food photo of a nano banana dish in a fancy restaurant with a Gemini theme" --output "outputs/gemini-wide.png" --aspectRatio "16:9" --imageSize "2K"\r
```\r
\r
```powershell\r
node ./skills/gemini-image-generation/scripts/edit-image.mjs --prompt "Turn this cat into a watercolor illustration eating a nano-banana in a fancy restaurant under the Gemini constellation" --input "inputs/cat.png" --output "outputs/cat-watercolor.png" --aspectRatio "5:4" --imageSize "2K"\r
```\r
\r
```powershell\r
node ./skills/gemini-image-generation/scripts/edit-image.mjs --prompt "Create an office group photo of these people making funny faces" --input "inputs/person-1.jpg" --input "inputs/person-2.jpg" --input "inputs/person-3.jpg" --output "outputs/group-photo.png"\r
```\r
\r
## Notes\r
\r
- The script prints `TEXT:` lines for model text and `IMAGE:` lines for each saved file.\r
- After the skill finishes, always present every generated image to the user by outputting `MEDIA:\x3Cpath>` for each saved image path. This ensures the image is rendered inline in the conversation alongside the file path.\r
- The final JSON summary only includes generated image paths and optional image config so prompts, model IDs, and source image paths are not echoed back into logs.\r
- Saved file extensions follow the returned image mime type. If the requested output path uses a different suffix, the scripts keep the base name and write the file with the returned type instead.\r
- If the model returns multiple images, the scripts save them as `name-1.png`, `name-2.png`, and so on.\r
- `edit-image.mjs` supports repeated `--input` flags. You can also pass a comma-separated list to a single `--input` value.\r
- `edit-image.mjs` infers the source mime type from `.png`, `.jpg`, `.jpeg`, or `.webp`. Use one `--mime-type` for all inputs, or repeat `--mime-type` so it lines up with each `--input`.\r
- Both scripts accept `--aspectRatio` and `--imageSize`. They also accept the kebab-case forms `--aspect-ratio` and `--image-size`.\r
- The scripts only send `config.imageConfig` when at least one of those parameters is provided.