ByteDanceFastHigh

PuLID

ByteDance PuLID: tuning-free identity customization on SDXL. Give it one face photo and a prompt to generate portraits in any scene or style — no training, 4-step fast sampling, and even two-identity blending. Extremely cost-effective at 2 credits per image.

6 credits

1 credit x num_samples (default 4 images = 6 credits)

Tuning-free identity preservation from a single face photo

Lightning-fast 4-step sampling on SDXL

mix_identities: blend two different faces into one person

fidelity vs 'extremely style' generation modes

Up to 8 images per run at just 2 credits each

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "bytedance/pulid",
  "input": {
    "main_face_image": "https://example.com/face.webp",
    "prompt": "portrait, impressionist painting, loose brushwork, vibrant color, light and shadow play",
    "num_samples": 4,
    "identity_scale": 0.8,
    "generation_mode": "fidelity"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	No	portrait,color,cinematic,in garden,soft light,detailed face	Text prompt describing the scene and style
`main_face_image`	string	Yes	-	ID image (main face photo)
`auxiliary_face_image1`	string	No	-	Additional ID image — the second face when mix_identities is on
`auxiliary_face_image2`	string	No	-	Additional ID image (auxiliary)
`auxiliary_face_image3`	string	No	-	Additional ID image (auxiliary)
`negative_prompt`	string	No	flaws in the eyes, flaws in the face, flaws, lowres, non-HDRi, low quality, worst quality,artifacts noise, text, watermark, glitch, deformed, mutated, ugly, disfigured, hands, low resolution, partially rendered objects, deformed or partially rendered eyes, deformed, deformed eyeballs, cross-eyed,blurry	Negative Prompt
`cfg_scale`	number	No	1.2	CFG, recommend value range [1, 1.5], 1 will be faster
`num_steps`	integer	No	4	Sampling steps (1-100). 4 is the fast lightning default
`image_height`	integer	No	1024	Output height in pixels (512-2024)
`image_width`	integer	No	768	Output width in pixels (512-2024)
`identity_scale`	number	No	0.8	ID scale (0-5). Higher preserves the face more strongly
`generation_mode`	string	No	fidelity	'fidelity' prioritizes likeness; 'extremely style' prioritizes stylization fidelityextremely style
`mix_identities`	boolean	No	false	Turn on to mix two ID images into one identity (use auxiliary_face_image1)
`seed`	integer	No	-	Random seed. Leave blank to randomize
`num_samples`	integer	No	4	Number of images to generate (1-8). Billed at 2 credits per image
`output_format`	string	No	webp	Format of the output images webpjpgpng
`output_quality`	integer	No	80	Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

How to Provide File Input

There are 3 ways to provide files for the main_face_imageauxiliary_face_image1 parameters:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=bytedance/pulid" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:main_face_image=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "bytedance/pulid",
  "input": {
    "prompt": "your prompt here",
    "main_face_image": "https://example.com/image.jpg"
  }
}

See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Impressionist Portrait Set

Four impressionist-painting portraits of the same person from one photo

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "bytedance/pulid",
  "input": {
    "main_face_image": "https://example.com/face.webp",
    "prompt": "portrait, impressionist painting, loose brushwork, vibrant color, light and shadow play",
    "num_samples": 4,
    "identity_scale": 0.8,
    "generation_mode": "fidelity"
  }
}'

Two-Face Identity Mix

Blend two face photos into a single new character

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "bytedance/pulid",
  "input": {
    "main_face_image": "https://example.com/face-a.jpg",
    "auxiliary_face_image1": "https://example.com/face-b.jpg",
    "mix_identities": true,
    "prompt": "portrait, color, cinematic, soft light, detailed face",
    "num_samples": 2
  }
}'