NVIDIA Sana

1.20 credits/MP
ae_sana

Create images from text prompts, with selectable styles, sizes, negative prompts, and output formats.

Image
1.20 credits/MP

Pricing

1.20 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.

1.20 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.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.image_sizeobject | stringNoThe size of the generated 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.num_imagesintegerNoThe number of images to generate.1
request_body.style_nameenum ((No style) | Cinematic | Photographic | Anime | Manga | Digital Art | Pixel art | Fantasy art | Neonpunk | 3D Model)NoThe style to generate the image in.(No style)
request_body.output_formatenum (jpeg | png)NoThe format of the generated image.jpeg
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. 5
request_body.negative_promptstringNo The negative prompt to use. Use it to address details that you don't want in the image. This could be colors, objects, scenery and even the small details (e.g. moustache, blurry, low resolution). ""
request_body.num_inference_stepsintegerNoThe number of inference steps to perform.18
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_sana' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "image_size": "portrait_16_9",
      "negative_prompt": "anime, cartoon, illustration, painting, 3D render, plastic skin, doll, airbrushed skin, oversaturated, exaggerated eyes, beauty filter, text, watermark",
      "num_images": 1,
      "output_format": "png",
      "prompt": "Photorealistic cinematic portrait of a real Chinese woman aged 23, shoulder-length black hair with natural straight bangs, wearing an ordinary light gray cotton hoodie. Waist-up, facing camera, quietly alert expression. Natural facial proportions, visible skin texture and pores, natural hair strands, understated makeup, authentic candid film still, realistic apartment bedroom at night, soft warm bedside lamp with gentle cool window light, photographic 50mm lens, believable exposure, natural colors, not glamorized, vertical portrait.",
      "style_name": "Photographic"
    }
  }
}'
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": "18c2cd16-9eb9-472a-a9b0-cacb722d014d"
}

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

Guides using this tool

See how this tool fits into real workflows