Qwen Image Edit Plus Lora

42.00 credits/MP
ae_qwen_image_edit_plus_lora

Edit one or more images with text instructions, including optional style controls, negative prompts, output sizing, and multiple variations.

Image
42.00 credits/MP

Pricing

42.00 AE credits per MP. Charge for successfully returned images. Charge proportionally to actual pixels. One MP is 1,000,000 pixels.

42.00 credits/MP

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedinteger | unknownNo The same seed and the same prompt given to the same version of the model will output the same image every time. —
request_body.lorasarrayNo The LoRAs to use for the image generation. You can use up to 3 LoRAs and they will be merged together to generate the final image. —
request_body.loras[].pathstringYesURL or the path to the LoRA weights.—
request_body.loras[].scalenumberNo The scale of the LoRA weight. This is used to scale the LoRA weight before merging it with the base model. 1
request_body.promptstringYesThe prompt to generate the image with—
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 | string | unknownNoThe size of the generated image. If not provided, the size of the final input image will be used to calculate the size of the output image.—
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 edit.—
request_body.num_imagesintegerNoThe number of images to generate.1
request_body.accelerationenum (none | regular)NoAcceleration level for image generation. Options: 'none', 'regular'. Higher acceleration increases speed. 'regular' balances speed and quality.regular
request_body.output_formatenum (jpeg | png)NoThe format of the generated image.png
request_body.guidance_scalenumberNo The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you. 4
request_body.negative_promptstringNoThe negative prompt for the generation
request_body.num_inference_stepsintegerNoThe number of inference steps to perform.28
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_qwen_image_edit_plus_lora' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "acceleration": "regular",
      "enable_safety_checker": true,
      "guidance_scale": 4,
      "image_size": {
        "height": 1024,
        "width": 1024
      },
      "image_urls": [
        "https://v3b.fal.media/files/b/0ab1e8ec/LtnUkEUYeArFr8YCOsUBr.png"
      ],
      "negative_prompt": "改变构图、改变姿势、改变取景、改变发型、改变发色、改变发饰、改变服装、改变配饰、改变头身比、改成写实或正常比例、多视图拼图、三视图、文字、水印、编号、对话框、第二个人物、背景道具、畸变手指、多瞳、面部不对称、脸部变形、模糊、拼接痕迹",
      "num_images": 1,
      "num_inference_steps": 28,
      "output_format": "png",
      "prompt": "保持输入图片完全不变:同一位 Q 版角色、同一姿势、同一构图与取景、同样的全身立绘、同样的纯白背景、同样的发型发色发饰、同样的服装配饰、同样的光影与圆润明快的赛璐璐画风、约 2.5 头身与超大蓝色圆眼。只把面部表情改为【困惑】:一侧眉毛上挑、大眼微微眯起露出疑惑神情、嘴微微张开,Q 版夸张可爱的表现。除眉毛、眼睛开合与高光、嘴型外,画面其余部分(发型、环形呆毛、女仆头饰、鳍状发饰、服装、围裙上的小鲸鱼图案、蓝宝石领结、鲸尾、短袜、玛丽珍鞋、姿势、构图、背景、光影、画风)必须与输入图完全一致。输出一张与输入构图完全一致的角色立绘。",
      "seed": 4029521948
    }
  }
}'
Response exampleresponse.json
JSONPartial content
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "129760cc-ff4d-4d21-a524-67b3ef9b1821"
}

This example shows part of the response. Copied content is valid JSON.