- Home
- AI Music APIs
- PATINA
PATINA
What it is
PATINA is a paid web and API tool for generating seamless PBR material textures from text prompts or image inputs. Text generation produces tiling materials with upscaling up to 8K, while image URLs can produce texture variations. An input image and mask can regenerate white mask regions while preserving black regions. The five available maps are basecolor, normal, roughness, metalness, and height. Tiling can run in both directions, horizontally, or vertically, with configurable tile size and stride. Requests support one to four texture images and one to eight denoising steps. Exports are PNG, JPEG, and WebP, with a maximum texture resolution of 8192 pixels. Prompt expansion is enabled by default and adds approximately $0.0025. The API provides JavaScript, Python, and cURL examples using a FAL_KEY environment variable. The listing marks commercial use, and pricing is per request: $0.01 base plus per-megapixel and map charges, with additional upscaling charges.
For and against
For
- Text and image texture generation
- Five PBR map types
- Seamless tiling controls
- Up to 8192-pixel textures
- PNG, JPEG, and WebP exports
Against
- Paid per-request pricing
- Prompt expansion adds approximately $0.0025
- Supports only one to four images per request
- Upscaling adds extra charges
The verdict
PATINA brings material generation, map creation, masking, and tiling controls into a web and API workflow. Per-request charges and optional upscaling costs should be considered before integration.
Who it suits
PATINA suits artists and developers needing text- or image-driven material generation with seamless tiling and PBR maps. Its API examples support programmatic integration.
Plans and prices
PATINA material inference
1K material with all 5 maps: $0.08 · 8K material with all 5 maps and 4x upscaling: $0.61
Read 7 Oct 2026 · fal.ai
On the record
- Commercial use
- The model listing is marked for commercial use.fal.ai · read 7 Oct 2026
- Dataset
- fal says PATINA's training dataset was built from CC0 material libraries including AmbientCG, Poly Haven, and other public-domain sources.blog.fal.ai · read 7 Oct 2026
- Developer access
- The API page provides JavaScript, Python, and cURL examples and uses a FAL_KEY environment variable for authentication.fal.ai · read 7 Oct 2026
- Generation limits
- The endpoint supports 1–4 texture images per request and 1–8 denoising steps.fal.ai · read 7 Oct 2026
- Inpainting
- An input image and mask can be used to regenerate white mask regions while preserving black regions.fal.ai · read 7 Oct 2026
- Maker background
- fal says it was founded in 2021 and is headquartered in San Francisco.fal.ai · read 7 Oct 2026
- Output maps
- The five available PBR maps are basecolor, normal, roughness, metalness, and height.fal.ai · read 7 Oct 2026
- Prompt controls
- Prompt expansion is enabled by default and adds approximately $0.0025.fal.ai · read 7 Oct 2026
- Related photo workflow
- The material extraction endpoint isolates a material from a photo, flattens it, makes it seamless, and predicts PBR maps.fal.ai · read 7 Oct 2026
- Safety
- The endpoint has an enabled-by-default safety checker option for filtering outputs.fal.ai · read 7 Oct 2026
- Support
- fal lists [email protected] as its contact address.fal.ai · read 7 Oct 2026
- Text to material
- Generates complete, seamlessly tiling PBR materials from text prompts, with upscaling up to 8K.fal.ai · read 7 Oct 2026
- Texture variations
- With an input image URL, the endpoint can create texture variations through image-to-image generation.fal.ai · read 7 Oct 2026
- Tiling controls
- Tiling can be set to both directions, horizontal, or vertical; tile size and stride are configurable.fal.ai · read 7 Oct 2026
