fal-ai/patina

PATINA - Image to PBR Maps

Endpoint: fal-ai/patina

Category: Image-to-image

Pricing: $0.01 base + $0.01 per megapixel per output map

Give PATINA an image that already looks the way you want, and it will predict a full set of PBR material maps from it. The image itself is not modified - it is analyzed to extract physically-based material properties.

When to use this

Use this endpoint when you already have a texture or photo and just need PBR maps generated from it. No changes are made to the original image.

Good for:

• A photo of a real surface (brick, wood, metal) that you want to use as a 3D material
• A texture from another tool that needs PBR data added
• Any flat image you want to turn into a full PBR material

Use a different endpoint if:

• You want to generate a new texture from a text description - use /patina/material
• You want to create variations of an existing texture - use /patina/material with image_url
• You have a photo of a scene and want to extract a specific material from it - use /patina/material/extract

Quick start

javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/patina", {
  input: {
    image_url: "https://example.com/my-texture.jpg"
  }
});

// result.data.images - array of PBR maps, each with a map_type

Input

Example request

json
{
  "image_url": "https://example.com/brick-wall.jpg",
  "maps": ["basecolor", "normal", "roughness", "metalness", "height"],
  "output_format": "png"
}

Output

Example response

json
{
  "images": [
    { "url": "https://fal.media/files/...", "map_type": "basecolor" },
    { "url": "https://fal.media/files/...", "map_type": "normal" },
    { "url": "https://fal.media/files/...", "map_type": "roughness" },
    { "url": "https://fal.media/files/...", "map_type": "metalness" },
    { "url": "https://fal.media/files/...", "map_type": "height" }
  ],
  "seed": 42
}

Output maps explained

Code examples

JavaScript

javascript
import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/patina", {
  input: {
    image_url: "https://example.com/my-texture.jpg"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);

Python

python
import fal_client

result = fal_client.subscribe(
    "fal-ai/patina",
    arguments={
        "image_url": "https://example.com/my-texture.jpg"
    },
    with_logs=True,
)
print(result)

cURL

bash
curl -X POST https://fal.run/fal-ai/patina \
  -H "Authorization: Key $FAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{"image_url": "https://example.com/my-texture.jpg"}'