Running a model
MicrosoftImage to 3DMicrosoft TRELLIS.2
High-fidelity image-to-3D generative model with compact structured latents
One of Auray's catalogue models: the same key, the same credits, the same job lifecycle as every other address.
Its request shape is published below. Whether it runs right now is GET /v1/catalogue's word, with no key needed: its addresses say connected for an address that runs, and a submit to any other is refused before anything is charged — described answers 501 model_not_connected, paused 503 model_disabled.
Category image-to-3d · Scope 3d:write (or external:write on an older key) · Price Credits per call (counted as settings.shapeSlat.steps+settings.sparseStructure.steps+settings.texSlat.steps@36*settings.decimationTarget@500000*settings.textureSize@2048): 2.669 for settings.resolution=1536; 3 for settings.resolution=512; settings.resolution=1024. Each band has its own least and most a request is counted at. Quoted when you submit, at the most the request can cost; the charge settles to what the job cost and never above the quote. The submit's answer carries the quote as credits_quoted, and credits_charged says what has been taken.
#Input
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
inputs | object | yes | — | |
inputs.image | string | yes | — | Image input (an http(s) URL; upload a local file first and send its read URL). A URL. |
inputs.meshFile | string | no | — | 3D model to re-texture (an http(s) URL; upload a local file first and send its read URL). Skips geometry generation and applies new textures using the reference image. A URL. |
seed | integer | no | — | Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range. Documented range: 0 to 9,223,372,036,854,776,000. |
settings | object | no | — | |
settings.resolution | integer | no | 1024 | Voxel grid resolution for 3D generation. Higher values capture finer geometric detail. One of 512, 1024, 1536. |
settings.alphaMode | string | no | "OPAQUE" | Material alpha mode for the output mesh. One of "OPAQUE", "BLEND", "MASK". |
settings.decimationTarget | integer | no | 500000 | Target polygon count for mesh simplification. Lower values produce lighter models at the cost of geometric detail. Documented range: 5,000 to 1,000,000. |
settings.dracoCompression | object | no | — | |
settings.dracoCompression.enabled | boolean | no | — | Compress the output GLB geometry with Draco. |
settings.dracoCompression.level | integer | no | 7 | Encoding effort for Draco compression. Higher values reduce file size further but encode more slowly. Documented range: 0 to 10. |
settings.dracoCompression.quantizationNormal | integer | no | 14 | Quantization bits for vertex normals. Higher values produce smoother shading at the cost of file size. Documented range: 8 to 30. |
settings.dracoCompression.quantizationPosition | integer | no | 16 | Quantization bits for vertex positions. Higher values preserve more positional detail at the cost of file size. Documented range: 8 to 30. |
settings.dracoCompression.quantizationTexCoord | integer | no | 14 | Quantization bits for texture coordinates. Higher values keep textures sharper at UV seams at the cost of file size. Documented range: 8 to 30. |
settings.meshCluster | object | no | — | |
settings.meshCluster.globalIterations | integer | no | 1 | Global iterations for chart clustering. Documented range: 0 to 64. |
settings.meshCluster.refineIterations | integer | no | 0 | Local refinement iterations for chart clustering. Documented range: 0 to 64. |
settings.meshCluster.smoothStrength | integer | no | 1 | Smoothing strength applied during chart clustering. Documented range: 0 to 10. |
settings.meshCluster.thresholdConeHalfAngleRad | number | no | 1.5707963267948966 | Cone half-angle threshold in radians used during UV chart clustering. Documented range: 0 to 3.142. |
settings.remesh | boolean | no | true | Whether to remesh the output for cleaner topology. |
settings.remeshBand | number | no | 1 | Narrow-band width in voxels used for dual-contouring remeshing. Documented range: up to 16. |
settings.remeshProject | number | no | 0 | Projection factor for snapping remeshed vertices back to the original surface. Documented range: up to 1. |
settings.shapeSlat | object | no | — | |
settings.shapeSlat.steps | integer | no | 12 | Number of denoising steps. More steps improve quality but increase generation time. Documented range: 1 to 50. |
settings.shapeSlat.guidanceIntervalEnd | number | no | 1 | End of the sampling schedule fraction over which guidance is applied. Documented range: 0 to 1. |
settings.shapeSlat.guidanceIntervalStart | number | no | 0.6 | Start of the sampling schedule fraction over which guidance is applied. Documented range: 0 to 1. |
settings.shapeSlat.guidanceRescale | number | no | 0.5 | Dampens oversaturation from high guidance values. Lower values apply more correction. Documented range: 0 to 1. |
settings.shapeSlat.guidanceStrength | number | no | 7.5 | How closely the output follows the input image. Higher values enforce stricter adherence to the visible geometry. Documented range: 1 to 10. |
settings.shapeSlat.rescaleT | number | no | 3 | Timestep rescaling factor for the sampling schedule. Controls how guidance strength is distributed across steps. Documented range: 1 to 6. |
settings.sparseStructure | object | no | — | |
settings.sparseStructure.steps | integer | no | 12 | Number of denoising steps. More steps improve quality but increase generation time. Documented range: 1 to 50. |
settings.sparseStructure.guidanceIntervalEnd | number | no | 1 | End of the sampling schedule fraction over which guidance is applied. Documented range: 0 to 1. |
settings.sparseStructure.guidanceIntervalStart | number | no | 0.6 | Start of the sampling schedule fraction over which guidance is applied. Documented range: 0 to 1. |
settings.sparseStructure.guidanceRescale | number | no | 0.7 | Dampens oversaturation from high guidance values. Lower values apply more correction. Documented range: 0 to 1. |
settings.sparseStructure.guidanceStrength | number | no | 7.5 | How closely the output follows the input image. Higher values enforce stricter adherence to the visible geometry. Documented range: 1 to 10. |
settings.sparseStructure.rescaleT | number | no | 5 | Timestep rescaling factor for the sampling schedule. Controls how guidance strength is distributed across steps. Documented range: 1 to 6. |
settings.texSlat | object | no | — | |
settings.texSlat.steps | integer | no | 12 | Number of denoising steps. More steps improve quality but increase generation time. Documented range: 1 to 50. |
settings.texSlat.guidanceIntervalEnd | number | no | 0.9 | End of the sampling schedule fraction over which guidance is applied. Documented range: 0 to 1. |
settings.texSlat.guidanceIntervalStart | number | no | 0.6 | Start of the sampling schedule fraction over which guidance is applied. Documented range: 0 to 1. |
settings.texSlat.guidanceRescale | number | no | 0 | Dampens oversaturation from high guidance values. Lower values apply more correction. Documented range: 0 to 1. |
settings.texSlat.guidanceStrength | number | no | 1 | How closely the output follows the input image. Higher values enforce stricter adherence to the visible geometry. Documented range: 1 to 10. |
settings.texSlat.rescaleT | number | no | 3 | Timestep rescaling factor for the sampling schedule. Controls how guidance strength is distributed across steps. Documented range: 1 to 6. |
settings.textureFormat | string | no | "WEBP" | Texture format for the output mesh. One of "WEBP", "PNG". |
settings.textureSize | integer | no | 2048 | Resolution of the output texture map in pixels. Higher values produce finer surface detail. Documented range: 1,024 to 4,096. |
outputType | string | no | "URL" | 3D output type. One of "URL". |
outputFormat | string | no | "GLB" | Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities. - `JPG`: Best for photorealistic images with smaller file sizes (no transparency). - `PNG`: Lossless compression, supports high quality and transparency (alpha channel). - `WEBP`: Modern format providing superior compression and transparency support. - `MP4`: Widely supported video container (H.264), recommended for general use. - `WEBM`: Optimized for web delivery. - `MOV`: QuickTime format, common in professional workflows (Apple ecosystem). - `GIF`: Animated image format (no audio), suitable for short loops or previews. - `MP3`: Compressed audio, smaller file size. - `WAV`: Uncompressed, high-quality audio. - `FLAC`: Lossless compression. - `OGG`: Open-source compressed audio format (Vorbis codec). - `SVG`: Scalable Vector Graphics. - `TIFF`: High-quality output supporting layers. - `GLB`: Binary glTF format for 3D models, including geometry, textures, and PBR materials. > [!NOTE] > **Transparency**: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., `PNG`, `WEBP`, `TIFF`). `JPG` does not support transparency. One of "GLB". |
idempotency_key | string | no | — | Your own name for this request. Send the same one twice and the second call is answered with the first request rather than charged again. Idempotency-Key: as a header is accepted as an alias — that is the spelling a retrying proxy replays, and the one to use when running a model on auray.run, where a request that outlives its connection is answered 504 and recovered by replay. Omit it and the platform mints one. 1 to 64 characters. |
#Rules
Across fields, as the model's documentation states them. Each is judged before anything is charged — warned with a Deprecation header until enforcement starts — and listed as JSON Schema under x-auray-rules in the openapi.json.
- When
inputs.meshFileis sent, do not send a request wheresettings.shapeSlatis sent, or wheresettings.sparseStructureis sent, or wheresettings.decimationTargetis sent, or wheresettings.remeshis sent, or wheresettings.remeshBandis sent, or wheresettings.remeshProjectis sent, or wheresettings.meshClusteris sent. - Unless
settings.dracoCompression.enabledis true, do not sendsettings.dracoCompression.level. Unlesssettings.dracoCompression.enabledis true, do not sendsettings.dracoCompression.quantizationNormal. Unlesssettings.dracoCompression.enabledis true, do not sendsettings.dracoCompression.quantizationPosition. Unlesssettings.dracoCompression.enabledis true, do not sendsettings.dracoCompression.quantizationTexCoord.
#Example
curl -X POST https://queue.auray.run/auray-serverless/microsoft/trellis-2-4b \
-H "Authorization: Bearer $AURAY_API_KEY" \
-H "content-type: application/json" \
-d '{
"inputs": {
"image": "https://v3b.auray.media/examples/samples/still-life.jpg"
}
}'import { createClient } from "@auray/client";
const auray = createClient(); // reads AURAY_API_KEY
const result = await auray.subscribe("auray-serverless/microsoft/trellis-2-4b", {
input: {
"inputs": {
"image": "https://v3b.auray.media/examples/samples/still-life.jpg"
}
},
onQueueUpdate: (update) => console.log(update.status),
});
console.dir(result, { depth: null });from auray_client import Client
auray = Client() # reads AURAY_API_KEY
result = auray.subscribe(
"auray-serverless/microsoft/trellis-2-4b",
input={
"inputs": {
"image": "https://v3b.auray.media/examples/samples/still-life.jpg"
}
},
on_queue_update=lambda update: print(update["status"]),
)
print(result){
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "run_model",
"arguments": {
"address": "auray-serverless/microsoft/trellis-2-4b",
"input": {
"inputs": {
"image": "https://v3b.auray.media/examples/samples/still-life.jpg"
}
}
}
}
}const res = await fetch("https://queue.auray.run/auray-serverless/microsoft/trellis-2-4b", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AURAY_API_KEY}`,
"content-type": "application/json",
},
body: JSON.stringify({
"inputs": {
"image": "https://v3b.auray.media/examples/samples/still-life.jpg"
}
}),
});
console.log(await res.json());import os, requests
r = requests.post(
"https://queue.auray.run/auray-serverless/microsoft/trellis-2-4b",
headers={"Authorization": f"Bearer {os.environ['AURAY_API_KEY']}"},
json={
"inputs": {
"image": "https://v3b.auray.media/examples/samples/still-life.jpg"
}
},
)
r.raise_for_status()
print(r.json())package main
import (
"bytes"
"fmt"
"io"
"net/http"
"os"
)
func main() {
body := []byte(`{
"inputs": {
"image": "https://v3b.auray.media/examples/samples/still-life.jpg"
}
}`)
req, err := http.NewRequest("POST", "https://queue.auray.run/auray-serverless/microsoft/trellis-2-4b", bytes.NewReader(body))
if err != nil {
panic(err)
}
req.Header.Set("Authorization", "Bearer "+os.Getenv("AURAY_API_KEY"))
req.Header.Set("Content-Type", "application/json")
res, err := http.DefaultClient.Do(req)
if err != nil {
panic(err)
}
defer res.Body.Close()
out, _ := io.ReadAll(res.Body)
fmt.Println(res.Status, string(out))
}<?php
$ch = curl_init("https://queue.auray.run/auray-serverless/microsoft/trellis-2-4b");
curl_setopt_array($ch, [
CURLOPT_CUSTOMREQUEST => "POST",
CURLOPT_RETURNTRANSFER => true,
CURLOPT_HTTPHEADER => [
"Authorization: Bearer " . getenv("AURAY_API_KEY"),
"Content-Type: application/json",
],
CURLOPT_POSTFIELDS => json_encode([
"inputs" => [
"image" => "https://v3b.auray.media/examples/samples/still-life.jpg",
],
], JSON_UNESCAPED_SLASHES | JSON_UNESCAPED_UNICODE),
]);
$response = curl_exec($ch);
echo curl_getinfo($ch, CURLINFO_HTTP_CODE), " ", $response, PHP_EOL;require "net/http"
require "json"
uri = URI("https://queue.auray.run/auray-serverless/microsoft/trellis-2-4b")
req = Net::HTTP::Post.new(uri)
req["Authorization"] = "Bearer #{ENV.fetch("AURAY_API_KEY")}"
req["Content-Type"] = "application/json"
req.body = {
"inputs" => {
"image" => "https://v3b.auray.media/examples/samples/still-life.jpg"
}
}.to_json
res = Net::HTTP.start(uri.hostname, uri.port, use_ssl: true) { |http| http.request(req) }
puts res.code, res.bodyimport java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
public class Main {
public static void main(String[] args) throws Exception {
String body = """
{
"inputs": {
"image": "https://v3b.auray.media/examples/samples/still-life.jpg"
}
}""";
HttpRequest request = HttpRequest.newBuilder()
.uri(URI.create("https://queue.auray.run/auray-serverless/microsoft/trellis-2-4b"))
.header("Authorization", "Bearer " + System.getenv("AURAY_API_KEY"))
.header("Content-Type", "application/json")
.method("POST", HttpRequest.BodyPublishers.ofString(body))
.build();
HttpResponse<String> response = HttpClient.newHttpClient()
.send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.statusCode() + " " + response.body());
}
}using System.Net.Http.Headers;
using System.Text;
using var client = new HttpClient();
client.DefaultRequestHeaders.Authorization =
new AuthenticationHeaderValue("Bearer", Environment.GetEnvironmentVariable("AURAY_API_KEY"));
using var request = new HttpRequestMessage(HttpMethod.Post, "https://queue.auray.run/auray-serverless/microsoft/trellis-2-4b");
var body = """
{
"inputs": {
"image": "https://v3b.auray.media/examples/samples/still-life.jpg"
}
}
""";
request.Content = new StringContent(body, Encoding.UTF8, "application/json");
using var response = await client.SendAsync(request);
Console.WriteLine($"{(int)response.StatusCode} {await response.Content.ReadAsStringAsync()}");The same body on https://auray.run runs synchronously and answers the result — unless it usually takes longer than a run may hold its connection, which is refused 400 model_not_synchronous before anything is charged. Options — ?webhook=, ?wait=, priority and timeout headers — are on Submit a request.
#Machine contracts
- openapi.json — this page as an OpenAPI 3.1 document, public.
- llms.txt — the same, written for an agent.