FLUX Pro Kontext Text To Image

From 48 credits/call
ae_flux_pro_kontext_text_to_image

Create one or more high-quality images from a text description, with control over aspect ratio, format, prompt strength, and seed.

Image
From 48 credits/call

Pricing

From 48 credits/call
ConditionCharge
Per image48 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.

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.promptstringYesThe 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.num_imagesintegerNoThe number of images to generate.1
request_body.aspect_ratioenum (21:9 | 16:9 | 4:3 | 3:2 | 1:1 | 2:3 | 3:4 | 9:16 | 9:21)NoThe aspect ratio of the generated image.1:1
request_body.output_formatenum (jpeg | png)NoThe format of the generated image.jpeg
request_body.enhance_promptbooleanNoWhether to enhance the prompt for better results.false
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. 3.5
request_body.safety_toleranceenum (1 | 2 | 3 | 4 | 5 | 6)NoThe 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-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_flux_pro_kontext_text_to_image' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "aspect_ratio": "3:4",
      "enhance_prompt": false,
      "guidance_scale": 4.5,
      "num_images": 1,
      "output_format": "png",
      "prompt": "An empty suit of ancient Chinese heavy lamellar armor made of thick black rhinoceros hide plates with dark gold bronze trim, mounted upright on an invisible display stand, no person inside, no face, no head, hollow helmet, dramatic rim lighting, pure black background, epic game card weapon art, highly detailed realistic leather and metal texture, centered single object filling the frame, NOT a landscape, NOT a person, no human, no text, no signature, no watermark"
    }
  }
}'
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": "a484c510-6f79-4533-8a9e-3800601b0e85"
}

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

Guides using this tool

See how this tool fits into real workflows