Five material maps
Predicts basecolor (albedo), normal, roughness, metalness and height (displacement) maps. The Maps option picks which ones.
Find objects and outlines
PATINA creates seamless high-resolution normal, roughness, basecolor (albedo), height (displacement) and metalness maps from images
Opens the image studio with PATINA Image to Maps ready to use. You can look around as a guest. Running it takes the Pro plan or higher.


What it makes
Find objects and outlines
Finds objects, depth, poses and outlines in a picture.
What you need
What you get
Masks, depth maps or outlines
PATINA Image to Maps turns a photograph or a computer-generated image (a render) into material maps. Material maps are a set of images that each describe one property of a surface. It has two ways to work. Image to Maps predicts maps from your image. Extract Material pulls a texture out of your image, guided by a prompt that says which texture you want.
The maps are basecolor (albedo), normal, roughness, metalness and height (displacement). The Maps option picks which of the five to predict, and all five are selected to begin with. In Extract Material you can also set more. Image Size sets the output texture dimensions in pixels. Strength sets how much your image is transformed. Upscale Factor enlarges the predicted maps. 0 means no upscaling. 2 and 4 mean twice and four times the resolution.
Each run costs 100 credits. In Extract Material, Enable Prompt Expansion is on to begin with. It expands your prompt for richer detail and adds about 0.0025 credits.
Same job: find objects and outlines. Compare before you choose.
Generate a 3D relief depth map with Hi3D from a single image.
Qwen-Image-Layered is a model capable of decomposing an image into multiple RGBA layers.
SAM 3.1 builds comes with Object Multiplex, a shared-memory approach for joint multi-object tracking that delivers faster speeds with larger number of objects tracked.
Splits a finished image into independent, editable transparent-PNG layers — background plus separate elements, from a text description, returning 2 to 17 layers per call for non-destructive reuse in design tools.
Predicts basecolor (albedo), normal, roughness, metalness and height (displacement) maps. The Maps option picks which ones.
Extract Material pulls a texture from your image, based on a prompt that says which texture you want.
In Extract Material, Upscale Factor enlarges the predicted maps: 0 means no upscaling, 2 gives twice the resolution and 4 gives four times.
Choose Image to Maps to predict maps, or Extract Material to pull a texture from your image.
Upload a photograph or a computer-generated image (a render). For Extract Material, also write a prompt that describes which texture to extract.
Choose the maps you want. In Extract Material you can also set Image Size, Strength and Upscale Factor. Then run. It costs 100 credits.
Turn a photograph or computer-generated image into basecolor, normal, roughness, metalness and height maps.
Describe the texture you want and pull it out of your image.
Quick answers to help you get the most out of PATINA Image to Maps in FunAI Studio.