Qwen3 Pro Image to Image

Endpoint

POST /images/generations

Full URL: https://modelfold.ai/v1/images/generations

Authentication: every request must include the Authorization: Bearer <API_KEY> header.

Send model parameters directly in the JSON body. Do not wrap them in input. This request waits for generation to finish and returns data[].url; supported media models also offer async jobs, polling and callbacks. Replace example media URLs with your own publicly accessible files. See API gateway for billing and errors.

Input parameters for the image-to-image generation task.

Request Parameters

Body (application/json)

Parameter	Type	Required	Description
model	string	Yes	The model name used for generation. This field is required. This endpoint must use the qwen3/pro-image-to-image model. Default："qwen3/pro-image-to-image"。 Allowed values：qwen3/pro-image-to-image。 Example：qwen3/pro-image-to-image。
image_urls	array<string>	Yes	Input image URL array. Upload images and provide their URLs rather than the file content. Supports up to 3 images. Supported file types: image/jpeg, image/png, image/webp, image/bmp, and image/gif,image/tiff. Maximum file size: 10 MB per image. minItems: 1. maxItems: 3.
prompt	string	Yes	Prompt required by the ModelFold gateway; at most 2000 characters. The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported. minLength: 1. maxLength: 2000. Example：Turn the input image into a cinematic watercolor illustration.。
resolution	string	No	The output image resolution. Default："1K"。 Allowed values：1K / 2K。 Example：1K。
image_size	string	No	The output image size. Default："16:9"。 Allowed values：1:1 / 3:2 / 2:3 / 4:3 / 3:4 / 16:9 / 9:16 / 21:9。 Example：1:1。
output_format	string	No	Output format: png or jpeg. Set this field explicitly. Allowed values：png / jpeg。 Example：png。
prompt_extend	boolean	No	Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt, which significantly improves results for simple descriptions. Default：true。 Example：true。
negative_prompt	string	No	The negative prompt that describes content you do not want to appear in the image. minLength: 0. maxLength: 5000. Example：blurry, low quality, distorted。
seed	integer	No	Random seed, 0–2147483647. If omitted, a random seed is used. minimum: 0. maximum: 2147483647. Example：1。
nsfw_checker	boolean	No	Whether to enable content filtering. Optional. Defaults to false. When set to false, content filtering is disabled and all results are returned directly by the model. Note: Content filtering cannot guarantee that all inappropriate content will be detected. If the filtering results do not meet your requirements, you must implement additional content moderation measures. Default：false。 Example：false。

Request Example

curl -X POST "https://modelfold.ai/v1/images/generations" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "qwen3/pro-image-to-image",
  "image_urls": [
    "https://example.com/reference.png"
  ],
  "prompt": "Turn the input image into a cinematic watercolor illustration.",
  "resolution": "1K",
  "image_size": "16:9",
  "prompt_extend": true,
  "nsfw_checker": false
}'

{
  "model": "qwen3/pro-image-to-image",
  "image_urls": [
    "https://example.com/reference.png"
  ],
  "prompt": "Turn the input image into a cinematic watercolor illustration.",
  "resolution": "1K",
  "image_size": "16:9",
  "prompt_extend": true,
  "nsfw_checker": false
}

Response

200 — Generation completed. usage contains actual billing details; result URLs are illustrative.

{
  "ok": true,
  "created": 1792134000,
  "data": [
    {
      "url": "https://modelfold.ai/uploads/outputs/result.png"
    }
  ],
  "usage": {}
}