Search VisionStory documentation

No documentation matched “”.

Try a feature or resource name such as , , or .

VisionStoryDevelopers
Get API key

Guide

AI Image Generation API

Generate or edit images from text prompts and reference media with the VisionStory API, then reuse the result in image-to-video workflows.

The VisionStory AI Image Generation API creates or edits images from text prompts and optional reference media. The synchronous response returns an image URL that you can download or pass directly into an image-to-video workflow.

Beta access. This endpoint is allowlisted during beta. If a request returns 403 / not enabled, contact your VisionStory representative. An active subscription is required.

AI image API endpoints

MethodPathWhat it does
GET/api/v1/image/modelsList image models with sizes and per-image credit cost
POST/api/v1/imageGenerate an image from a prompt (+ optional references)

List image generation models

Shell
curl -s -H "X-API-Key: $VISIONSTORY_API_KEY" https://openapi.visionstory.ai/api/v1/image/models

Each model reports its aspect ratios, resolutions, reference-image limit, and credit_per_image. Current models: nano-banana (fast, economical), nano-banana-2 (balanced, strong edits), nano-banana-pro (highest quality, supports 2K). Drive your integration from this endpoint rather than hardcoding.

Generate or edit an AI image

Send a model_id (from the models endpoint) and a prompt. Optionally add up to 4 refs (reference images) to guide style or subject, or to edit — editing works through instructions in the prompt plus reference images, no mask needed.

Shell
curl -s -X POST -H "X-API-Key: $VISIONSTORY_API_KEY" -H "Content-Type: application/json" -d '{"model_id": "nano-banana", "prompt": "A red panda barista in a cozy cafe, warm lighting", "aspect_ratio": "1:1", "resolution": "1K"}' https://openapi.visionstory.ai/api/v1/image
JSON
{
  "data": {
    "url": "https://cdn.visionstory.ai/example.png"
  }
}
  • Aspect ratio: one of 1:1 (default) / 2:3 / 3:2 / 3:4 / 4:3 / 4:5 / 5:4 / 9:16 / 16:9 / 21:9.
  • Resolution: 1K (default) or 2K.
  • References: up to 4, each asset_id / url / inline_data.

Use a generated image in a video

The returned url is a normal image URL — pass it straight into other endpoints, e.g. as first_frame or refs for AI Video:

JSON
{
  "model_id": "seedance-2.0",
  "prompt": "the scene gently comes alive, slow camera push-in",
  "first_frame": {
    "url": "https://cdn.visionstory.ai/example.png"
  }
}

Billing, limits, and storage

  • Not stored by default. The image is returned as a URL but not added to your asset library — upload it via POST /api/v1/asset if you want a reusable asset_id.
  • Billing: credits per image (see credit_per_image from the models endpoint), charged only on success.
  • Concurrency: synchronous generation is capped at a few concurrent requests per key during beta; excess requests are rejected rather than queued.