# FLUX PuLID

> ⚡️FLUX PuLID: FLUX-dev based Pure and Lightning ID Customization via Contrastive Alignment🎭

- **Provider**: replicate
- **Model ID**: bytedance/flux-pulid
- **Category**: face_image_generation
- **Credits**: 47 per request
- **Pricing Type**: input_based

## API Endpoint

Base URL: https://api.core.today/v1

### Create Prediction
POST /predictions

### Get Status
GET /predictions/{job_id}

### Cancel
DELETE /predictions/{job_id}

## Authentication

Header: `X-API-Key: YOUR_API_KEY`

## Input Parameters

- `true_cfg` (number, optional): Set the Classifier-Free Guidance (CFG) scale. 1.0 uses standard CFG, while values >1.0 enable True CFG for more precise control over generation. Higher values increase adherence to the prompt at the cost of image quality. (Default: `1`; Range: min: 1, max: 10)
- `num_outputs` (integer, optional): Set the number of images to generate (1-4) (Default: `1`; Range: min: 1, max: 4)
- `seed` (integer, optional): Set a random seed for generation (leave blank or -1 for random)
- `main_face_image` (string, **required**): Upload an ID image for face generation
- `max_sequence_length` (integer, optional): Set the max sequence length for prompt (T5), smaller is faster (128-512) (Default: `128`; Range: min: 128, max: 512)
- `output_quality` (integer, optional): Set the quality of the output image for jpg and webp (1-100) (Default: `80`; Range: min: 1, max: 100)
- `num_steps` (integer, optional): Set the number of denoising steps (1-20) (Default: `20`; Range: min: 1, max: 20)
- `start_step` (integer, optional): Set the timestep to start inserting ID (0-4 recommended, 0 for highest fidelity, 4 for more editability) (Default: `0`; Range: min: 0, max: 10)
- `id_weight` (number, optional): Set the weight of the ID image influence (0.0-3.0) (Default: `1`; Range: min: 0, max: 3)
- `output_format` (string, optional): Choose the format of the output image (Default: `webp`; Options: `png`, `jpg`, `webp`)
- `negative_prompt` (string, optional): Enter a negative prompt to specify what to avoid in the image (Default: `bad quality, worst quality, text, signature, watermark, extra limbs, low resolution, partially rendered objects, deformed or partially rendered eyes, deformed, deformed eyeballs, cross-eyed, blurry`)
- `guidance_scale` (number, optional): Set the guidance scale for text prompt influence (1.0-10.0) (Default: `4`; Range: min: 1, max: 10)
- `width` (integer, optional): Set the width of the generated image (256-1536 pixels) (Default: `896`; Range: min: 256, max: 1536)
- `prompt` (string, optional): Enter a text prompt to guide image generation (Default: `portrait, color, cinematic`)
- `height` (integer, optional): Set the height of the generated image (256-1536 pixels) (Default: `1152`; Range: min: 256, max: 1536)

## Example Request

```json
{
  "model": "bytedance/flux-pulid",
  "input": {
    "true_cfg": 1,
    "num_outputs": 4,
    "main_face_image": "https://replicate.delivery/pbxt/MayZhLThspqLqRhirB8VEjqbEX5B0PWqjd9xe3PkTv2wLMcr/woman.png",
    "max_sequence_length": 128,
    "output_quality": 80,
    "num_steps": 20,
    "start_step": 4,
    "id_weight": 1,
    "output_format": "webp",
    "negative_prompt": "bad quality, worst quality, text, signature, watermark, extra limbs",
    "guidance_scale": 4,
    "width": 896,
    "prompt": "a woman holding sign with glowing green text \"PuLID for FLUX\"",
    "height": 1152
  }
}
```

## Response Format

```json
{
  "job_id": "abc123",
  "status": "pending",
  "provider": "replicate",
  "model": "black-forest-labs/flux-schnell",
  "created_at": "2026-01-01T00:00:00Z",
  "result": null,
  "error": null
}
```

Status values: `pending`, `processing`, `completed`, `failed`, `cancelled`

## Usage Flow

1. POST /predictions with model and input → receive job_id
2. Poll GET /predictions/{job_id} until status is `completed` or `failed`
3. Result contains output URL(s) or data

## Output Type

url

## Tags

bytedance, pulid, flux, identity-preserving, face-generation, avatar

## Documentation

https://replicate.com/bytedance/flux-pulid