Hunyuan Image 3 Instruct Gpu Edit

From 108.00 credits
ae_hunyuan_image_3_instruct_gpu_edit

Edit, transform, or restyle up to three reference images using a written instruction, with control over size, output format, and number of results.

Image
From 108.00 credits

Pricing

108.00 AE credits per MP. Charge on total returned-image MP, rounded to two decimal places; non-empty successful output has a minimum charge of 1 MP per call. One MP is 1024 by 1024 pixels.

From 108.00 credits

Starting price applies to successful image results within the minimum 1-MP tier.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedinteger | unknownNoRandom seed for reproducible results. If None, a random seed is used.—
request_body.promptstringYesThe text prompt to generate an image from.—
request_body.sync_modebooleanNoIf `True`, the media will be returned as a data URI and the output data won't be available in the request history.false
request_body.image_sizeobject | stringNoThe desired size of the generated image. If auto, image size will be determined by the model.auto
request_body.image_size.widthintegerNoThe width of the generated image.512
request_body.image_size.heightintegerNoThe height of the generated image.512
request_body.image_urlsarrayYesThe URLs of the images to use as a reference for the generation. A maximum of 3 images are supported.—
request_body.num_imagesintegerNoThe number of images to generate.1
request_body.output_formatenum (jpeg | png)NoThe format of the generated image.png
request_body.guidance_scalenumberNoControls how much the model adheres to the prompt. Higher values mean stricter adherence.3.5
request_body.enable_safety_checkerbooleanNoIf set to true, the safety checker will be enabled.true

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_hunyuan_image_3_instruct_gpu_edit' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "enable_safety_checker": true,
      "guidance_scale": 4.5,
      "image_size": {
        "height": 1024,
        "width": 1024
      },
      "image_urls": [
        "https://agentearth.ai/fileserver/file/40b4ce8c-6d77-4bd8-903f-3c93dc2da33e.jpeg"
      ],
      "num_images": 1,
      "output_format": "png",
      "prompt": "参照参考图最左侧的棕色卡通马,画一张正方形构图的角色插画:这只马闭着眼睛、张大嘴打喷嚏、嘴边飞出口水小水滴,脖子上挂完整的 EMP ID 工牌,暖棕色马身与深棕鬃毛。马匹完整地待在画面正中间,四周都留出空白,身体下方有自然的收尾(可见胸部与前腿上部),绝对不要在画面边缘被裁切。浅薄荷绿微渐变背景,马身后一圈柔和白色光晕与淡放射线。扁平 2D 卡通、粗黑描边、赛璐璐平涂上色、幽默职场漫画风。不要其它动物、办公家具和文字。"
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "f8c05dcd-c4c0-4785-bbb4-4076a0c6de43"
}