SKILL.md
Image Edit
Edits an existing image using a text prompt (image-to-image transformation).
Command
agent-media image edit --in <path> --prompt <text> [options]Inputs
| Option | Required | Description |
|---|---|---|
--in |
Yes | Input file path or URL |
--prompt |
Yes | Text description of the desired edit |
--out |
No | Output path, filename or directory (default: ./) |
--provider |
No | Provider to use (default: auto-detect) |
--model |
No | Model override (e.g., fal-ai/flux-2/edit) |
Output
Returns a JSON object with the edited image path:
{
"ok": true,
"media_type": "image",
"action": "edit",
"provider": "fal",
"output_path": "edited_123_abc.png",
"mime": "image/png",
"bytes": 567890
}Examples
Edit an image:
agent-media image edit --in photo.jpg --prompt "make the sky more vibrant"Add elements to an image:
agent-media image edit --in portrait.png --prompt "add sunglasses"Edit with specific provider:
agent-media image edit --in scene.jpg --prompt "change to night time" --provider replicateProviders
This action requires an external provider:
- fal - Requires
FALAPIKEY - replicate - Requires
REPLICATEAPITOKEN - runpod - Requires
RUNPODAPIKEY - ai-gateway - Requires
AIGATEWAYAPI_KEY
The local provider does not support image editing.