IP Adapter Face ID

24 credits/call
ae_ip_adapter_face_id

ae_ip_adapter_face_id — Generate an image with WaveSpeed FLUX-PuLID from a text prompt and one reference image, aiming to carry the reference face's likeness into the result. Provide prompt and image in request_body. Optional settings include output size, guidance scale, seed, and JPEG, PNG, or WebP format. Processing is asynchronous; retain the returned task ID to check status and retrieve outputs. The tool identifier is retained, but the current model is FLUX-PuLID, not the original IP-Adapter or legacy SDXL/Kolors models. Only current schema settings are supported; multiple reference images, mixed identities, and exact likeness are not guaranteed.

Image
24 credits/call

Pricing

24 credits/call
ConditionCharge
Each call24 credits/call

The fixed fee is 24 credits per call.

Applies to calls using WaveSpeed FLUX-PuLID to generate an image from a text prompt and a single reference image.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedintegerNoThe random seed to use for the generation. -1 means a random seed will be used.—
request_body.sizestringNoThe size of the generated media in pixels (width*height).1024*1024
request_body.imagestringYesNo parameter description.—
request_body.promptstringYesThe positive prompt for the generation.—
request_body.output_formatenum (jpeg | png | webp)NoThe format of the output image.jpeg
request_body.guidance_scalenumberNoThe guidance scale to use for the generation.3.5

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_ip_adapter_face_id' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "guidance_scale": 4.5,
      "image": "https://litter.catbox.moe/v8ixlv.jpg",
      "output_format": "jpeg",
      "prompt": "Full body photograph of this exact same man, identity preserved perfectly: middle-aged Chinese man, completely bald shaved head, broad round full face with soft double chin, very thick straight black eyebrows sitting low over the eyes, small narrow dark eyes with single eyelids, large protruding ears, wide flat nose, full lips, tanned skin, neutral calm expression without smiling. Standing straight facing the camera, full length visible from head to shoes, hands relaxed at sides. Wearing a bespoke navy pinstripe three-piece suit with peak lapels, white dress shirt, dark purple silk tie, gold cufflinks, white pocket square, polished black leather oxford shoes. Luxury penthouse office interior, dark marble reflective floor, floor-to-ceiling windows, dusk city skyline behind. Cinematic soft rim light, photorealistic editorial photography, sharp focus on face, high detail, no text, no watermark.",
      "seed": -1,
      "size": "1024*1536"
    }
  }
}'
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": "ec0d110f-0049-40ee-bea7-b71861450c65"
}

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