Generate Image

This document describes the /v1/platform API series, supporting image and video generation for Tencent Cloud Hunyuan, Jimeng, Kling and other AIGC models. All APIs are wrapped in a unified format, abstracting underlying differences.

POST /v1/platform/image

Submit an AI image generation task. Tasks execute asynchronously; the API returns task_id. Poll for results via the Query Task API

⚠️ File URLs generated by this API are only retained for 7 days. Please download and save them promptly.

Request Parameters

application/json

Parameter	Type	Required	Description
model	string	Required	Model identifier, must start with image-. Format: image-{model_name}-{version}, e.g. image-kling-2.1.
prompt	string	Required	Positive text description for image generation. Supports Chinese and English. Recommend describing scene content, style, composition, etc. in detail.
negative_prompt	string	Optional	Negative prompt describing content you don't want in the image, e.g. blurry, low quality, watermark.
enhance_prompt	string	Optional	Whether to enable automatic prompt optimization and enhancement. 可选值：enabled / disabled
generation_mode	string	Optional	Generation mode. Refer to the model documentation for available values. Examples: image-to-image, inpainting, etc.
inputs	array	Optional	List of input files for reference images, style images, etc. (image-to-image). ↳ inputs[i] child fields
output	object	Optional	Output configuration controlling image resolution, storage mode, etc. ↳ output child fields
input_region	string	Optional	Source region of input material. 可选值：mainland / oversea
session_id	string	Optional	Deduplication identifier. If a request with the same session_id was made within 3 days, this request returns an error. Max 50 characters. Leave empty to skip deduplication.
session_context	string	Optional	Source context for passing user request info. The field value is returned in task callbacks. Max 1000 characters.
ext_info	object	Optional	Reserved field for special purposes. The specific format is determined by the model used.

inputs[i] child fields

Field Name	Type	Required	Description
url	string	Required	Publicly accessible URL of the input image. Recommend images under 7 MB. Supported formats: jpeg, jpg, png, webp.
text	string	Optional	Description of the input image to help the model understand the content. Currently only GEM 2.5 and GEM 3.0 are effective.

output child fields

Field Name	Type	Required	Description
resolution	string	Optional	Resolution of the generated image. Available values per model: • GEM 2.5 / 3.0：1K、2K、4K，Default 1K • Vidu q2：1080p、2K、4K，Default 1080p • Kling 2.1：1k、2k，Default 1k • Hunyuan 3.0：720P、1080P、2K、4K
aspect_ratio	string	Optional	Specify the aspect ratio of the generated image. Mutually exclusive with width/height, takes priority. Available values per model: • GEM：1:1、3:2、2:3、3:4、4:3、4:5、5:4、9:16、16:9、21:9 • Qwen：Not supported yet • Hunyuan：16:9、9:16、1:1、4:3、3:4、3:2、2:3、21:9 • Vidu：16:9、9:16、1:1、3:4、4:3、21:9、2:3、3:2 • Kling：16:9、9:16、1:1、4:3、3:4、3:2、2:3、21:9
width	integer	Optional	Output image width (pixels). Auto-calculates aspect ratio when specified with height. Ignored if aspect_ratio is set.
height	integer	Optional	Output image height (pixels). Used together with width.
media_name	string	Optional	Output media filename, max 64 characters. Defaults to a system-generated filename.
class_id	integer	Optional	Category ID for media classification management. Default: 0 (other).
input_compliance_check	string	Optional	Whether to enable compliance check on input content. 可选值：enabled / disabled
output_compliance_check	string	Optional	Whether to enable compliance check on output content. 可选值：enabled / disabled
person_generation	string	Optional	Whether to allow generation of people or faces. 可选值：allow_adult / disallowed allow_adult allows generating adults; disallowed prohibits people or faces in the image.

Request Example

JSON (Text-to-Image)

{
  "model":  "image-kling-2.1",
  "prompt": "A cute orange cat sitting under a cherry blossom tree, watercolor style, high detail",
  "negative_prompt": "blurry, low quality, watermark, distorted",
  "enhance_prompt": "enabled",
  "output": {
    "aspect_ratio": "1:1",

  }
}

JSON (Image-to-Image)

{
  "model":  "image-jimeng-3.0",
  "prompt": "Transform the image into cyberpunk neon style",
  "generation_mode": "image_to_image",
  "inputs": [
    {
      "url": "https://example.com/source.jpg"
    }
  ],
  "output": {
    "aspect_ratio": "16:9"
  }
}

Response Parameters

Field Name	Type	Description
task_id	string	Unique task ID for subsequent task status queries.
status	string	Initial task status, usually queued.

Response Example

JSON · 200 OK

{
  "task_id": "img_abc123xyz456",
  "status":  "queued"
}