Image

Flux PuLID

Credit-based pricing. Supports reference images, batch up to 4.

Try Flux PuLID →Compare models

Output

image

Aspect ratio

1:1, 16:9, 9:16, 4:3, 3:4

Resolution

1024

Max batch

Inputs

Reference image (required)

Batch up to 4 per request

Example prompt

The same person in a sun-drenched Santorini café, wearing a white linen dress, soft morning light, editorial fashion photography

Try this prompt →

LLM-ready

API & LLM schema

Exact request contract for this model. Agents can fetch it from /api/v1/models?id=fal-ai/flux-pulid.

POST/api/v1/generate20 fields · 3 required

Field	Type	Requirement	Contract
`model_id`	constant	Required	ArtEmotion model identifier.
`extra`	object	Optional	Model-specific settings may also be nested here.
`max_credits`	number	Optional	Reject before submission if the estimated list price exceeds this cap. · Range: 1–…
`webhook_url`	string	Optional	Format: uri
`webhook_secret`	string	Optional	Optional model input.
`folder_id`	string	Optional	Optional model input.
`prompt`	string	Required	Optional model input.
`num_inference_steps`	number	Optional	Number of denoising steps. Higher = more detail. · Default: 20 · Range: 1–50
`id_weight`	number	Optional	Strength of face identity preservation. Higher = closer match to the reference. · Default: 1 · Range: 0–1
`guidance_scale`	number	Optional	How closely the model follows the prompt. · Default: 4 · Range: 0–20
`true_cfg`	number	Optional	True classifier-free guidance scale. 1 uses the faster distilled guidance; above 1 switches to real CFG. · Default: 1 · Range: 1–10
`start_step`	number	Optional	Denoising step at which identity conditioning kicks in. Later start = more prompt freedom, weaker likeness. · Default: 0 · Range: 0–50
`max_sequence_length`	string	Optional	Maximum prompt token length. Longer allows more detailed prompts at some speed cost. · Allowed: 128, 256, 512 · Default: 128
`negative_prompt`	string	Optional	Elements to exclude from the generated image. · Default:
`enable_safety_checker`	boolean	Optional	Whether to enable the safety checker. · Default: true
`seed`	integer	Optional	Random seed for reproducibility.
`aspect_ratio`	string	Optional	Allowed: 1:1, 16:9, 9:16, 4:3, 3:4
`resolution`	string	Optional	Allowed: 1024
`num_images`	integer	Optional	Range: 1–4
`reference_image_url`	string	Required	Format: uri

Minimal request example

{
  "model_id": "fal-ai/flux-pulid",
  "prompt": "The same person in a sun-drenched Santorini café, wearing a white linen dress, soft morning light, editorial fashion photography",
  "reference_image_url": "https://example.com/reference_image"
}

Raw JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://www.artemotion.ai/api/v1/models?id=fal-ai%2Fflux-pulid",
  "title": "Flux PuLID generation request",
  "description": "Request body accepted by POST /api/v1/generate for fal-ai/flux-pulid.",
  "type": "object",
  "properties": {
    "model_id": {
      "type": "string",
      "const": "fal-ai/flux-pulid",
      "description": "ArtEmotion model identifier."
    },
    "extra": {
      "type": "object",
      "additionalProperties": true,
      "description": "Model-specific settings may also be nested here."
    },
    "max_credits": {
      "type": "number",
      "minimum": 1,
      "description": "Reject before submission if the estimated list price exceeds this cap."
    },
    "webhook_url": {
      "type": "string",
      "format": "uri",
      "maxLength": 2048
    },
    "webhook_secret": {
      "type": "string",
      "maxLength": 512
    },
    "folder_id": {
      "type": "string"
    },
    "prompt": {
      "type": "string"
    },
    "num_inference_steps": {
      "title": "Steps",
      "description": "Number of denoising steps. Higher = more detail.",
      "default": 20,
      "type": "number",
      "minimum": 1,
      "maximum": 50,
      "multipleOf": 1
    },
    "id_weight": {
      "title": "Identity Weight",
      "description": "Strength of face identity preservation. Higher = closer match to the reference.",
      "default": 1,
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "multipleOf": 0.05
    },
    "guidance_scale": {
      "title": "Guidance Scale",
      "description": "How closely the model follows the prompt.",
      "default": 4,
      "type": "number",
      "minimum": 0,
      "maximum": 20,
      "multipleOf": 0.5
    },
    "true_cfg": {
      "title": "True CFG",
      "description": "True classifier-free guidance scale. 1 uses the faster distilled guidance; above 1 switches to real CFG.",
      "default": 1,
      "type": "number",
      "minimum": 1,
      "maximum": 10,
      "multipleOf": 0.5
    },
    "start_step": {
      "title": "ID Start Step",
      "description": "Denoising step at which identity conditioning kicks in. Later start = more prompt freedom, weaker likeness.",
      "default": 0,
      "type": "number",
      "minimum": 0,
      "maximum": 50,
      "multipleOf": 1
    },
    "max_sequence_length": {
      "title": "Max Sequence Length",
      "description": "Maximum prompt token length. Longer allows more detailed prompts at some speed cost.",
      "default": "128",
      "type": "string",
      "enum": [
        "128",
        "256",
        "512"
      ]
    },
    "negative_prompt": {
      "title": "Negative Prompt",
      "description": "Elements to exclude from the generated image.",
      "default": "",
      "type": "string"
    },
    "enable_safety_checker": {
      "title": "Enable Safety Checker",
      "description": "Whether to enable the safety checker.",
      "default": true,
      "type": "boolean"
    },
    "seed": {
      "title": "Seed",
      "description": "Random seed for reproducibility.",
      "type": "integer"
    },
    "aspect_ratio": {
      "type": "string",
      "enum": [
        "1:1",
        "16:9",
        "9:16",
        "4:3",
        "3:4"
      ]
    },
    "resolution": {
      "type": "string",
      "enum": [
        "1024"
      ]
    },
    "num_images": {
      "type": "integer",
      "minimum": 1,
      "maximum": 4
    },
    "reference_image_url": {
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "model_id",
    "prompt",
    "reference_image_url"
  ],
  "additionalProperties": false
}

Browse schemas for every ArtEmotion model →

FAQ

How much does Flux PuLID cost on ArtEmotion?

Credit-based pricing. You pay in ArtEmotion credits — every plan and top-up converts USD to credits at a fixed rate.

Do I get my credits back if Flux PuLID fails?

Yes — failed generations are never charged. The credits are released back to your balance automatically.

Can I call Flux PuLID from the API?

Yes. Use POST /api/v1/generate with model_id: "fal-ai/flux-pulid". See the API reference for the full schema.

Where are my generations stored?

Every output is saved to your personal Library. You can export or delete everything any time from Privacy & deletion.

Ready to generate with Flux PuLID?

Start now →

No commitment. New accounts get 50 free credits on signup. See pricing.