FLUX Pro Kontext Multi
From 48 credits/call
ae_flux_pro_kontext_multi
Create or edit images using text instructions and one or more reference images for complex visual transformations.
From 48 credits/call
Pricing
From 48 credits/call
| Condition | Charge |
|---|---|
| Per image | 48 credits/image |
Charges depend on image count.
An omitted image count is charged as one image.
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 prompt to generate an image from. | — |
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_urls | array | Yes | Image prompt for the omni model. | — |
request_body.num_images | integer | No | The number of images to generate. | 1 |
request_body.aspect_ratio | string | unknown | No | The aspect ratio of the generated image. | — |
request_body.output_format | enum (jpeg | png) | No | The format of the generated image. | jpeg |
request_body.enhance_prompt | boolean | No | Whether to enhance the prompt for better results. | false |
request_body.guidance_scale | number | No | 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. | 3.5 |
request_body.safety_tolerance | enum (1 | 2 | 3 | 4 | 5 | 6) | No | The safety tolerance level for the generated image. 1 being the most strict and 5 being the most permissive. | 2 |
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_flux_pro_kontext_multi' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"image_urls": [
"https://file.gw.xnetwk.net/file/cd65b287-c9f6-45dc-a331-7ca8af7df975.jpg",
"https://file.gw.xnetwk.net/file/a283ac51-d3dc-4cd7-bf96-b73ff1bf51d5.jpg"
],
"num_images": 1,
"prompt": "Image 1 is the REFERENCE photo of the individual cow (identity and coat pattern source). Image 2 is an AI-edited image whose pose, head angle, stance, background, lighting and composition are ALL APPROVED and must remain completely UNTOUCHED.\n\nONLY TASK: repaint the coat patches on the cow'\''s body in image 2 so the patch layout matches image 1, as if the very same individual cow were photographed in this new pose:\n- A large continuous dark red-brown patch covering the neck, shoulder and chest area, with the same irregular contour as in image 1.\n- Broken dark red-brown patches along the top of the back with white gaps between them, same shapes and rhythm as image 1.\n- Belly and lower flank mostly white, as in image 1.\n- Hindquarter mostly white with a few small dark patches near the tail root and on the upper hind leg, as in image 1.\n- Dark patch shape on the mid-barrel matching image 1.\n- White head, white legs, white tail switch, yellow ear tag kept unchanged.\nPatch edges must be irregular and natural with fine fur transitions. Do NOT change pose, head, legs, background, grass, sky, shadows, lighting or framing. Photorealistic."
}
}
}'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": "24c0ebd8-167e-4f7c-82ba-374d12b96f76"
}This example shows part of the response. Copied content is valid JSON.

