Generate a picture
generate_imageGenerates one to four pictures with a genframe model and charges the account's credits (price per picture is in list_models; failed pictures are refunded). Returns the picture(s) and download links. Waits up to about 50 seconds; if a picture is still in progress, the result gives its job_id for get_job. Pictures with real people are allowed only as the person's own photos; the content policy of genframe.ai applies.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"prompt": "<prompt>"
},
"name": "generate_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| size | No | Size option if the model has one, e.g. 1K, 2K, 4K (see list_models options.size). | |
| count | No | How many pictures (each is charged). Default 1. | |
| model | No | Model id from list_models. Default: a fast, cheap general model. | |
| prompt | Yes | What to draw. Any language. 3–1500 characters. | |
| quality | No | Quality option if the model has one (see list_models options.quality). | |
| aspect_ratio | No | For example 1:1, 4:5, 9:16, 16:9, 3:2. The nearest ratio the model makes is used. | |
| negative_prompt | No | What must not be in the picture (only models with negative: true). | |
| reference_image_urls | No | Optional reference pictures: public https URLs (JPG, PNG, WebP up to 8 MB) or links returned by this server. Only for models with refMax > 0. | |
| transparent_background | No | Transparent background (only models with alpha: true). |