PATINA Material - Text to PBR Material
Endpoint: fal-ai/patina/material
Category: Text-to-image (also supports image-to-image)
Pricing: $0.01 base + $0.02 per megapixel + $0.01 per megapixel per map. Upscaling adds $0.004 (2x) or $0.016 (4x) per megapixel per map.
Generate complete, seamlessly tiling PBR materials from text prompts - up to 8K resolution with built-in upscaling. Also supports image-to-image for creating variations of existing textures.
When to use this
Use this endpoint to generate new PBR materials from scratch using a text description, or to create variations of an existing texture via image-to-image.
Good for:
- Creating new materials from a text prompt ("weathered copper patina", "rough hewn limestone")
- Generating seamlessly tiling textures at up to 2048px (8K with upscaling)
- Creating variations on an existing texture using
image_url (pure image-to-image, not an edit)
- Inpainting regions of a texture using
image_url + mask_image_url
Use a different endpoint if:
- You already have a finished texture and just want PBR maps from it - use
/patina
- You have a photo of a scene and want to extract a specific material from it - use
/patina/material/extract
Quick start
Text to material
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("fal-ai/patina/material", {
input: {
prompt: "weathered copper patina with verdigris"
}
});
// result.data.images - generated texture + PBR maps
Image-to-image (create variations)
const result = await fal.subscribe("fal-ai/patina/material", {
input: {
prompt: "mossy stone wall",
image_url: "https://example.com/stone-texture.jpg",
strength: 0.75
}
});
| Parameter | Type | Required | Default | Description |
|---|
prompt | string | Yes | - | Text description of the material to generate |
image_size | string or object | No | square_hd | A named size, or an object like {"width": 1024, "height": 2048} |
num_inference_steps | integer | No | 8 | Number of denoising steps (1-8) |
seed | integer | No | Random | Seed for reproducible generation |
num_images | integer | No | 1 | Number of texture images to generate (1-4) |
enable_prompt_expansion | boolean | No | true | Expand prompt with an LLM for richer detail. Adds ~$0.0025. |
enable_safety_checker | boolean | No | true | Enable safety filtering on outputs |
tiling_mode | string | No | "both" | Tiling direction: both, horizontal, or vertical |
tile_size | integer | No | 128 | Tile size in latent space (64 = 512px, 128 = 1024px). Range: 32-256 |
tile_stride | integer | No | 64 | Tile stride in latent space. Range: 16-128 |
image_url | string | No | - | Input image URL for image-to-image. Without mask_image_url, creates variations. With it, performs inpainting. |
mask_url | string | No | - | Mask image for inpainting. White regions are regenerated, black regions are preserved. Requires image_url. |
strength | float | No | 0.75 | How much to transform the input image. Only used with image_url. |
maps | string[] | No | All five | Which PBR maps to predict: basecolor, normal, roughness, metalness, height. Deselect all to skip PBR estimation. |
upscale_factor | integer | No | 0 | Upscale via SeedVR seamless: 0 (none), 2 (2x), or 4 (4x) |
output_format | string | No | "png" | Output format: jpeg, png, or webp |
Example request (text only)
{
"prompt": "mossy stone wall",
"image_size": "square_hd",
"maps": ["basecolor", "normal", "roughness", "metalness", "height"]
}
Example request (image-to-image)
{
"prompt": "mossy stone wall",
"image_url": "https://example.com/stone-texture.jpg",
"strength": 0.75,
"maps": ["basecolor", "normal", "roughness", "metalness", "height"]
}
Output
| Field | Type | Description |
|---|
images | (ImageFile | MapImageFile)[] | The generated texture (no map_type) followed by PBR maps (each with map_type). |
seed | integer | Seed used for generation |
prompt | string | The prompt used (may differ from input if prompt expansion was enabled) |
timings | object | Timing breakdown in seconds |
Example response
{
"images": [
{ "url": "https://fal.media/files/..." },
{ "url": "https://fal.media/files/...", "map_type": "basecolor" },
{ "url": "https://fal.media/files/...", "map_type": "height" },
{ "url": "https://fal.media/files/...", "map_type": "normal" },
{ "url": "https://fal.media/files/...", "map_type": "roughness" },
{ "url": "https://fal.media/files/...", "map_type": "metalness" }
],
"seed": 42,
"prompt": "mossy stone wall"
}
The first image (without map_type) is the generated texture itself. The rest are the PBR maps.
Output maps explained
| Map | What it represents |
|---|
| Base Color | The surface color (albedo). What the material looks like without lighting effects. |
| Normal | Per-pixel surface orientation. Adds fine detail and bumps without changing geometry. |
| Roughness | How rough or smooth each point is. Controls reflection sharpness. |
| Metalness | Whether each point is metallic or dielectric. Affects how light reflects and refracts. |
| Height | Elevation data. Can be used for parallax mapping or actual mesh displacement. |
Code examples
JavaScript
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("fal-ai/patina/material", {
input: {
prompt: "mossy stone wall"
},
logs: true,
onQueueUpdate: (update) => {
if (update.status === "IN_PROGRESS") {
update.logs.map((log) => log.message).forEach(console.log);
}
},
});
console.log(result.data);
Python
import fal_client
result = fal_client.subscribe(
"fal-ai/patina/material",
arguments={
"prompt": "mossy stone wall"
},
with_logs=True,
)
print(result)
cURL
curl -X POST https://fal.run/fal-ai/patina/material \
-H "Authorization: Key $FAL_KEY" \
-H "Content-Type: application/json" \
-d '{"prompt": "mossy stone wall"}'
