Patina Material
Playground
Try it on WaveSpeedAI!PATINA Material generates complete seamlessly tiling PBR material sets (basecolor, normal, roughness, metalness, height) from text prompts — perfect for game engines, 3D rendering, and material libraries. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Patina Material generates a complete set of seamlessly tiling PBR material maps from a text description. Describe any surface — weathered wood, cracked clay, brushed metal — and the model produces a full material map set ready for use in game engines, 3D tools, and real-time rendering pipelines.
- Have a reference image? Try Patina Image-to-Map to generate maps from an existing photo.
Why Choose This?
-
Text-driven PBR generation Generate complete material map sets from a natural language description — no reference photo or manual authoring required.
-
Seamless tiling control Choose omnidirectional tiling (both), horizontal-only, or vertical-only to match your specific UV mapping and surface application needs.
-
Custom output size Specify any output resolution to match your target quality and performance requirements.
-
Production-ready output Maps are formatted for direct use in game engines (Unreal, Unity), 3D tools (Blender, Maya), and real-time rendering pipelines.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the material to generate (e.g. “weathered oak wood planks”, “cracked desert clay”). |
| size | No | Output dimensions in width×height pixels. Default: 1024×1024. |
| tiling_mode | No | Seamless tiling direction: both (default), horizontal, or vertical. |
How to Use
- Write your prompt — describe the material surface, condition, and style (e.g. “mossy cobblestone path, wet, medieval”).
- Set size (optional) — specify output dimensions to match your target resolution.
- Choose tiling_mode (optional) — select both for omnidirectional tiling, or horizontal/vertical for axis-specific tiling.
- Submit — the model generates all 6 PBR material maps in a single run.
- Download your complete tileable map set ready for use in your 3D pipeline.
Pricing
Just $0.48 per run (6 maps).
Best Use Cases
- Game development — Generate complete tileable PBR materials from text for environments, props, and terrain.
- 3D environment art — Rapidly produce material sets for architectural visualization and scene building without sourcing reference photography.
- Texture authoring — Create unlimited material variations from descriptive prompts for large-scale asset production.
- Indie & rapid prototyping — Quickly populate 3D scenes with physically accurate, seamlessly tiling materials.
- Procedural content pipelines — Integrate text-driven material generation into automated asset creation workflows.
Pro Tips
- Be specific in your prompt — include material type, condition, age, and surface characteristics (e.g. “polished black granite with fine white veining” rather than just “granite”).
- Specify environmental context for more accurate weathering and aging effects (e.g. “salt-worn, coastal, sun-bleached”).
- Use tiling_mode = horizontal for road or fabric materials that only repeat along one axis.
- Use tiling_mode = both for floor, wall, and terrain materials that tile in all directions.
Notes
- Only prompt is required; size and tiling_mode are optional.
- Each run generates 6 PBR map types as output.
- Please ensure your content complies with WaveSpeed AI’s usage policies.
Related Models
- Patina Image-to-Map — Generate PBR maps from an existing photograph or render.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"size": "1024*1024",
"tiling_mode": "both"
}
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/material" \
-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
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | Text description of the material to generate (e.g., 'weathered oak wood planks', 'cracked desert clay'). | |
| size | string | No | 1024*1024 | - | The size of the generated material maps in pixels (width*height). |
| tiling_mode | string | No | both | both, horizontal, vertical | Seamless tiling direction. 'both' tiles in all directions; 'horizontal' or 'vertical' tiles only along one axis. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |