FLUX Pulid
Usage-based pricing
ae_flux_pulid
Create images from a text prompt while preserving the identity of a person in a reference image.
Usage-based pricing
Pricing
The charge per call is (max(39.96 × generated image megapixels, 0)) AE credits. All applicable conditions are combined to calculate the total.
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.true_cfg | number | No | The weight of the CFG loss. | 1 |
request_body.id_weight | number | No | The weight of the ID loss. | 1 |
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 | No | The size of the generated image. | landscape_4_3 |
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.start_step | integer | No | The number of steps to start the CFG from. | 0 |
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. | 4 |
request_body.negative_prompt | string | No | The prompt to generate an image from. | "" |
request_body.max_sequence_length | enum (128 | 256 | 512) | No | The maximum sequence length for the model. | 128 |
request_body.num_inference_steps | integer | No | The number of inference steps to perform. | 20 |
request_body.reference_image_url | string | Yes | URL of image to use for inpainting. | — |
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_flux_pulid' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"guidance_scale": 3,
"id_weight": 1,
"image_size": {
"height": 1400,
"width": 1050
},
"negative_prompt": "beauty filter, airbrushed skin, plastic smooth skin, porcelain doll face, idealized face, instagram face, heavy retouching, glowing skin, cgi, 3d render, hyperreal, glamour makeup, perfect symmetry, blank stare, blurry, text, watermark, colored background, casual clothes",
"num_inference_steps": 30,
"output_format": "jpeg",
"prompt": "Unedited documentary portrait photograph of an Asian man in his mid-30s, a physician, waist-up composition, standing square to the camera, looking into the lens with a confident slight closed-mouth smile, wearing a dark navy suit jacket, white dress shirt and dark red silk necktie, black rectangular eyeglasses, short black hair, light moustache, plain white studio wall, shot on 35mm lens with natural even light, real photographic texture with visible skin pores, fine facial hair and subtle under-eye shadows, slightly uneven skin tone, no beauty retouching, no airbrushing, authentic candid professional photograph, head occupying about 30 percent of the frame height, no text, no watermark",
"reference_image_url": "https://agentearth.ai/fileserver/file/1dde8222-ad78-470b-9294-44cac7dd0302.jpg",
"seed": 550711
}
}
}'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": "d2f19a9d-fb06-414e-bd39-22c82e4d567e"
}This example shows part of the response. Copied content is valid JSON.

