Patina Image To Map

Patina Image To Map

Playground

PATINA generates seamless high-resolution PBR material maps (basecolor, normal, roughness, metalness, height) from a single image, ready for use in Unreal, Unity, Blender, and other 3D pipelines. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Patina Image-to-Map generates a complete set of PBR (Physically Based Rendering) material maps from a single input image. Upload any photograph or render — the model produces all 5 map types in one run, ready for use in game engines, 3D tools, and real-time rendering pipelines.

Why Choose This?

• Complete PBR map generation Generates all 5 material maps from a single image in one run — no manual authoring or separate processing steps required.

• Works on any surface image Compatible with photographs of real-world materials, textures, and renders for versatile workflow integration.

• Production-ready output Maps are formatted for direct use in game engines (Unreal, Unity), 3D tools (Blender, Maya), and real-time rendering pipelines.

• Simple single-input workflow Just one image in, five maps out. No configuration required.

Parameters

How to Use

1. Upload your image — provide a photograph or render of the surface material via URL.
2. Submit — the model generates all 5 PBR material maps in a single run.
3. Download your complete map set ready for use in your 3D pipeline.

Pricing

Just $0.06 per run (5 maps).

Best Use Cases

• Game development — Generate complete PBR material sets from photo references for real-time game assets.
• 3D environment art — Rapidly produce material maps for architectural visualization and scene building.
• Texture authoring — Accelerate material creation workflows by generating map sets from existing photography.
• Asset digitization — Convert photographs of real-world surfaces into production-ready PBR materials.
• Indie & rapid prototyping — Quickly populate 3D scenes with physically accurate materials without manual map authoring.

Pro Tips

• Use well-lit, evenly illuminated surface photos for the most accurate albedo and normal map extraction.
• Avoid images with strong directional shadows — diffuse, neutral lighting produces the cleanest maps.
• Crop your input image to focus on the material surface and minimize irrelevant background areas.
• High-resolution input images produce more detailed and accurate map outputs.

Notes

• image is the only required field.
• Each run generates 5 PBR map types as output.
• Ensure image URLs are publicly accessible if using a link rather than a direct upload.
• Please ensure your content complies with WaveSpeed AI’s usage policies.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/patina/image-to-map" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters