Firered Image Edit V1 1
39.00 credits/MP
ae_firered_image_edit_v1_1
Edit one or more images with a written instruction, including virtual try-ons, style changes, and portrait makeup.
39.00 credits/MP
Pricing
39.00 AE credits per MP. Charge for successfully returned images. Round each image up to a whole MP, then sum. One MP is 1,000,000 pixels.
39.00 credits/MP
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
request_body | object | Yes | No parameter description. | — |
request_body.seed | integer | unknown | No | The same seed and the same prompt given to the same version of the model will output the same image every time. | — |
request_body.prompt | string | Yes | The editing instruction describing what changes to make to the image. Supports both English and Chinese instructions. | — |
request_body.sync_mode | boolean | No | If `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_size | object | string | unknown | No | The size of the generated image. If None, uses the input image dimensions. | — |
request_body.image_size.width | integer | No | The width of the generated image. | 512 |
request_body.image_size.height | integer | No | The height of the generated image. | 512 |
request_body.image_urls | array | Yes | The URLs of the images to edit. Supports single image editing and multi-image references (e.g., virtual try-on, style transfer from reference, portrait makeup). | — |
request_body.num_images | integer | No | The number of images to generate. | 1 |
request_body.acceleration | enum (none | regular | high) | No | The acceleration level to use for inference speed optimization. | regular |
request_body.output_format | enum (jpeg | png) | No | The format of the generated image. | png |
request_body.guidance_scale | number | No | Classifier-free guidance scale. Higher values make the model follow the prompt more closely. | 4 |
request_body.negative_prompt | string | No | The negative prompt for the generation. | "" |
request_body.num_inference_steps | integer | No | The number of inference steps to perform. More steps generally produce higher quality results. | 30 |
request_body.enable_safety_checker | boolean | No | If 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-KeySubmit 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_firered_image_edit_v1_1' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"guidance_scale": 4,
"image_urls": [
"https://agentearth.ai/fileserver/file/7328579d-63ff-49f0-81f3-f4a12770c9ac.jpg"
],
"num_images": 1,
"num_inference_steps": 30,
"output_format": "jpeg",
"prompt": "Transform this SketchUp model screenshot into a photorealistic natural landscape photograph. Give every surface true-to-life materials: weathered quarry rock cliffs, natural meadow grass, realistic leafy trees, timber cabin with real wood grain and glass, calm blue pond with reflections and natural stone edging, real canvas parasols and wooden picnic tables, stone paving. Natural warm sunlight, physically accurate soft shadows, professional architectural photography color and exposure. CRITICAL PRESERVATION: keep the exact same viewpoint, perspective, framing and aspect ratio, and keep every object at its exact original position, size, shape and proportional relationship. Do not add, remove, move, resize or rearrange any element. No illustration, no cartoon, no low-poly 3D look."
}
}
}'Response exampleresponse.json
{
"description": "task accepted; poll the result via query_tool with this task_id",
"query_tool": "ae_get_result",
"status": "created",
"task_id": "a372e60d-1df5-4ceb-b9f6-c513ef36f3a8"
}This example shows part of the response. Copied content is valid JSON.







