Meshy V6 Lite Retexture API Documentation
Playground
Try it on WaveSpeedAI!Meshy 6 Lite Retexture re-textures an existing 3D model from a text prompt or a reference image. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Meshy 6 Lite Retexture generates new textures for an existing 3D model using a text description or reference image. Explore different materials, colors, and surface details while keeping the original model geometry.
Why Choose This?
- Retexture existing models — Change the materials, colors, and surface appearance of an existing 3D asset.
- Text or image guidance — Describe the desired texture or provide a reference image.
- PBR material support — Generate metallic, roughness, and normal maps when needed.
- UV control — Reuse the model’s existing UV layout or generate a new one.
- Simple workflow — Upload a model, provide texture guidance, and generate a new textured asset.
Parameters
| Parameter | Required | Description |
|---|---|---|
| model | Yes | Source 3D model in GLB, GLTF, FBX, OBJ, or STL format. |
| prompt | Conditional | Text description of the desired texture, materials, colors, and surface style. Provide a prompt or texture_image. |
| texture_image | Conditional | Reference image used to guide the texture style. If both prompt and texture_image are supplied, the reference image takes priority. |
| enable_pbr | No | Generate PBR maps including metallic, roughness, and normal maps. Default: false. |
| enable_original_uv | No | Reuse the model’s existing UV layout. Default: true. Disable it to generate a new UV layout. |
How to Use
- Upload a model — Provide the 3D asset you want to retexture.
- Add texture guidance — Describe the desired appearance or provide a reference image.
- Configure materials optional — Enable PBR maps when needed.
- Choose UV handling optional — Keep the original UV layout or generate a new one.
- Submit — Generate and retrieve the retextured model.
Pricing
$0.40 per model.
The prompt, reference image, PBR setting, and UV setting do not add separate charges.
Best Use Cases
- Material variations — Explore different materials and finishes on the same 3D model.
- Product visualization — Create new colors and surface treatments for product assets.
- Game assets — Produce texture variations without regenerating geometry.
- Style exploration — Apply different visual directions using text or image references.
- PBR workflows — Generate material maps for lighting-sensitive rendering.
Pro Tips
- Describe materials, colors, finish, wear, and surface properties clearly.
- Use a reference image with a consistent material or visual style.
- Keep
enable_original_uv=truewhen the model already has a suitable UV layout. - Disable original UV preservation when the model has missing or unsuitable UVs.
- Enable PBR when metallic, roughness, and normal maps are needed.
Notes
- Provide at least one of
promptortexture_image. - If both are supplied,
texture_imagetakes priority. enable_pbrdefaults tofalse.enable_original_uvdefaults totrue.- PBR output includes metallic, roughness, and normal maps.
- Meshy 6 Lite does not generate an emission map.
- A reference image with a substantially different object shape may be harder to match to the source model.
- Reusing the original UV layout works best when the source model already has suitable UV coordinates.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"model": "example",
"enable_pbr": false,
"enable_original_uv": true
}
JSON
)
# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
--connect-timeout 10 --max-time 60 \
-X POST "https://api.wavespeed.ai/api/v3/meshy/v6-lite/retexture" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}"); then
printf 'Submit failed. %s\n' "${CHECK}" >&2
exit 1
fi
TASK=$(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. %s\n' "${CHECK}" >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"
# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
# Transient errors (429, 5xx) are retried, honoring Retry-After.
HTTP_CODE=$(curl --silent --show-error --fail-with-body \
--connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
--output "${BODY_FILE}" --write-out '%{http_code}' \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
case "${HTTP_CODE}" in
2??) ;;
000|429|5??) # dropped connection or temporary error: keep polling
printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
sleep 10; continue ;;
*) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
cat "${BODY_FILE}" >&2; exit 1 ;;
esac
RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted)
printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneRetry temporary errors only while polling, never the submit request. Errors, retries and timeouts
Parameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| model | string | Yes | - | - | The 3D model to process (GLB, GLTF, FBX, OBJ or STL). |
| prompt | string | No | 0 ~ 600 characters | Describe the texture style. Provide a prompt or a texture_image. | |
| texture_image | string | No | - | - | Reference image for the texture style. Used when no prompt is given. |
| enable_pbr | boolean | No | false | - | Generate PBR maps. |
| enable_original_uv | boolean | No | true | - | Keep the model's own UVs. |
Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.
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.status | string | Task status. completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses. |
| 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.status | string | Status: completed is successful; failed, cancelled, timeout, and deleted are failure terminal statuses |
| 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 |