Image from Text

Generate images from text prompts using Gemini, Gemini Pro, Midjourney, or Grok. Optionally provide reference images to guide the output style or composition.

Endpoint

POST /v1/vidsheet/{id}/cells/{cell_id}/generate?agent_id={agent_id}

Path parameters

Parameter	Type	Description
`id`	integer	The sheet ID.
`cell_id`	integer	The cell ID.

Query parameters

Parameter	Type	Description
`agent_id`	integer	The agent ID.

Models

Model	`generation_type`	`data.model`
Gemini (choose `version`)	`image_from_text`	`"gemini"`
Gemini Pro	`image_from_text`	`"gemini_pro"`
Gemini 2	`image_from_text`	`"gemini_2"`
Gemini 2 Lite	`image_from_text`	`"gemini_2_lite"`
Imagen	`image_from_text`	`"imagen"`
Seedream 4.0	`image_from_text`	`"seedream-4.0"`
Seedream 4.5	`image_from_text`	`"seedream-4.5"`
GPT Image 2	`image_from_text`	`"gpt-image-2"`
GPT Image 2.5 Flare	`image_from_text`	`"gpt-image-2.5-flare"`
GPT Image 2.5 Sunburst	`image_from_text`	`"gpt-image-2.5-sunburst"`
Midjourney	`image_from_text`	`"midjourney"`
Grok	`image_from_text`	`"grok"`

Request body

Field	Type	Required	Description
`generation_type`	string	Yes	`"image_from_text"`.
`data.prompt`	string	Yes	Text description of the image to generate. Supports `{{variable_name}}` syntax.
`data.model`	string	No	One of `"gemini"`, `"gemini_pro"`, `"gemini_2"`, `"gemini_2_lite"`, `"imagen"`, `"seedream-4.0"`, `"seedream-4.5"`, `"gpt-image-2"`, `"gpt-image-2.5-flare"`, `"gpt-image-2.5-sunburst"`, `"midjourney"`, `"grok"`.
`data.version`	string	No	With `model: "gemini"` only — Nano Banana generation: `"nano-banana"`, `"nano-banana-pro"`, `"nano-banana-2"`, `"nano-banana-2-lite"`.
`data.aspect_ratio`	string	No	`"1:1"`, `"9:16"`, `"16:9"`, `"4:3"`, or `"3:4"`. Grok also supports `"3:2"` and `"2:3"`.
`data.number_of_images`	integer	No	Number of images to generate. Default `1`.
`data.content_resource_ids`	array	No	Array of content resource IDs to use as reference images.
`data.prompt_var`	string	No	Variable name to map the prompt value from a column.

Response (201)

{
  "generation_id": 9010,
  "status": "pending"
}

Once complete, the generated images are available in output_resources. Poll with GET /v1/generations/{generation_id} to check status.

Example

curl -X POST "https://api.gen.pro/v1/vidsheet/101/cells/3050/generate?agent_id=42" \
  -H "X-API-Key: your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "generation_type": "image_from_text",
    "data": {
      "prompt": "A futuristic cityscape at sunset with neon lights reflecting off glass buildings, cinematic style",
      "model": "gemini_pro",
      "aspect_ratio": "16:9",
      "number_of_images": 2
    }
  }'

Completed generation

{
  "id": 9010,
  "status": "completed",
  "user_job_type": "image_generation",
  "result": null,
  "failed_reason": null,
  "output_resources": [
    {
      "id": 1600,
      "url": "https://cdn.gen.pro/outputs/img_001.png",
      "thumbnail_url": "https://cdn.gen.pro/thumbnails/img_001.jpg",
      "object_type": "image",
      "type": "output"
    },
    {
      "id": 1601,
      "url": "https://cdn.gen.pro/outputs/img_002.png",
      "thumbnail_url": "https://cdn.gen.pro/thumbnails/img_002.jpg",
      "object_type": "image",
      "type": "output"
    }
  ],
  "execution_cost": 1.0
}

Cell configuration

Field	Type	Description
`model`	string	Default model: one of `"gemini"`, `"gemini_pro"`, `"gemini_2"`, `"gemini_2_lite"`, `"imagen"`, `"seedream-4.0"`, `"seedream-4.5"`, `"gpt-image-2"`, `"gpt-image-2.5-flare"`, `"gpt-image-2.5-sunburst"`, `"midjourney"`, `"grok"`.
`ratio`	string	Default aspect ratio: `"1:1"`, `"9:16"`, `"16:9"`, `"4:3"`, or `"3:4"`. Grok also supports `"3:2"` and `"2:3"`.
`autoGenerate`	boolean	Auto-trigger generation when dependent variables change.