Text to 3D Endpoint

Overview

The Text to 3D endpoint generates a 3D object from a text-based prompt.

Open in Playground 🚀

Request

--request POST 'https://modelslab.com/api/v6/3d/text_to_3d' \

Make a POST request to https://modelslab.com/api/v6/3d/text_to_3d endpoint and pass the required parameters as a request body.

Body Attributes

Parameter	Description	Values
key (required)	API key for request authorization.	String
prompt (required)	Text prompt to describe the 3D model to generate.	Default: "A full body mesh of a dog"
resolution (required)	Resolution of the generated 3D model.	Integer (max: 512, default: 256)
output_format (optional)	Format of the generated 3D model.	obj, stl, ply (default: glb)
render (optional)	Whether to render a NeRF video of the generated 3D model.	Boolean (default: false)
negative_prompt (optional)	Text to exclude specific elements from the generated model.	String (default: "")
guidance_scale (optional)	Balances the adherence to the prompt versus creativity in the generation.	Float (default: 1.0)
num_inference_steps (optional)	Number of steps for generating the 3D model.	Integer (default: 10)
ss_guidance_strength (optional)	Strength of style-space guidance for refinement.	Float (default: 7.5)
ss_sampling_steps (optional)	Number of steps for style-space sampling.	Integer (range: 1–50, default: 12)
slat_guidance_strength (optional)	Strength of slat guidance for model details.	Float (range: 0.0–10.0, default: 3.0)
slat_sampling_steps (optional)	Number of steps for slat guidance sampling.	Integer (range: 1–50, default: 12)
mesh_simplify (optional)	Degree of mesh simplification to optimize the output model.	Float (range: 0.90–0.98, default: 0.90)
foreground_ratio (optional)	Ratio of the foreground size to the overall image size (used if remove_bg is enabled).	Float (default: 0.85)
remove_bg (optional)	Removes the background from the generated model if enabled.	Boolean (default: false)
chunk_size (optional)	Size of processing chunks (affects VRAM usage).	Integer (max: 12000, default: 8192)
seed (optional)	Random seed for reproducibility; 0 generates a random seed.	Integer (default: 0)
temp (optional)	Save output files in a temporary directory when set to "yes".	String (default: "no")

Open in Playground 🚀

Example

Body

Body

{
    "key": "",
    "foreground_ratio": "0.85",
    "prompt": "a ghost wearing white bedsheet",
    "num_inference_steps": "30",
    "resolution": 512,
    "guidance_scale": "3",
    "ss_sampling_steps": 50,
    "slat_sampling_steps": 50,
    "seed": 0,
    "temp": "no",
    "webhook": null,
    "track_id": null
}

Request

JS

var myHeaders = new Headers();
myHeaders.append("Content-Type", "application/json");

var raw = JSON.stringify({
    "key": "",
    "foreground_ratio": "0.85",
    "prompt": "a ghost wearing white bedsheet",
    "num_inference_steps": "30",
    "resolution": 512,
    "guidance_scale": "3",
    "ss_sampling_steps": 50,
    "slat_sampling_steps": 50,
    "seed": 0,
    "temp": "no",
    "webhook": null,
    "track_id": null
});

var requestOptions = {
  method: 'POST',
  headers: myHeaders,
  body: raw,
  redirect: 'follow'
};

fetch("https://modelslab.com/api/v6/3d/text_to_3d", requestOptions)
  .then(response => response.text())
  .then(result => console.log(result))
  .catch(error => console.log('error', error));

PHP

<?php

$payload = [
    "key" => "",
    "foreground_ratio" => "0.85",
    "prompt" => "a ghost wearing white bedsheet",
    "num_inference_steps" => "30",
    "resolution" => 512,
    "guidance_scale" => "3",
    "ss_sampling_steps" => 50,
    "slat_sampling_steps" => 50,
    "seed" => 0,
    "temp" => "no",
    "webhook" => null,
    "track_id" => null
];

$curl = curl_init();

curl_setopt_array($curl, array(
  CURLOPT_URL => 'https://modelslab.com/api/v6/3d/text_to_3d',
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => '',
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 0,
  CURLOPT_FOLLOWLOCATION => true,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => 'POST',
  CURLOPT_POSTFIELDS => json_encode($payload),
  CURLOPT_HTTPHEADER => array(
    'Content-Type: application/json'
  ),
));

$response = curl_exec($curl);

curl_close($curl);
echo $response;

NODE

var request = require('request');
var options = {
  'method': 'POST',
  'url': 'https://modelslab.com/api/v6/3d/text_to_3d',
  'headers': {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    "key": "",
    "foreground_ratio": "0.85",
    "prompt": "a ghost wearing white bedsheet",
    "num_inference_steps": "30",
    "resolution": 512,
    "guidance_scale": "3",
    "ss_sampling_steps": 50,
    "slat_sampling_steps": 50,
    "seed": 0,
    "temp": "no",
    "webhook": null,
    "track_id": null
  })
};

request(options, function (error, response) {
  if (error) throw new Error(error);
  console.log(response.body);
});

PYTHON

import requests
import json

url = "https://modelslab.com/api/v6/3d/text_to_3d"

payload = json.dumps({
    "key": "",
    "foreground_ratio": "0.85",
    "prompt": "a ghost wearing white bedsheet",
    "num_inference_steps": "30",
    "resolution": 512,
    "guidance_scale": "3",
    "ss_sampling_steps": 50,
    "slat_sampling_steps": 50,
    "seed": 0,
    "temp": "no",
    "webhook": null,
    "track_id": null
})

headers = {
  'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

JAVA

OkHttpClient client = new OkHttpClient().newBuilder()
  .build();
MediaType mediaType = MediaType.parse("application/json");
RequestBody body = RequestBody.create(mediaType, "{\r\n    \"key\" : \"\",\r\n    \"foreground_ratio\": \"0.85\",\r\n    \"prompt\": \"a ghost wearing white bedsheet\",\r\n    \"num_inference_steps\": \"30\",\r\n    \"resolution\": 512,\r\n    \"guidance_scale\": \"3\",\r\n    \"ss_sampling_steps\": 50,\r\n    \"slat_sampling_steps\": 50,\r\n    \"seed\": 0,\r\n    \"temp\": \"no\",\r\n    \"webhook\": null,\r\n    \"track_id\": null\r\n}");
Request request = new Request.Builder()
  .url("https://modelslab.com/api/v6/3d/text_to_3d")
  .method("POST", body)
  .addHeader("Content-Type", "application/json")
  .build();
Response response = client.newCall(request).execute();

Response

{
    "status": "success",
    "generationTime": 15.47,
    "id": 109657557,
    "output": [
        "https://pub-3626123a908346a7a8be8d9295f44e26.r2.dev/out/ba5dd616-eb74-482c-8ee8-f8046687a8f3.obj"
    ],
    "proxy_links": [
        "https://cdn2.stablediffusionapi.com/out/ba5dd616-eb74-482c-8ee8-f8046687a8f3.obj"
    ],
    "meta": {
        "chunk_size": 8192,
        "file_prefix": "ba5dd616-eb74-482c-8ee8-f8046687a8f3",
        "foreground_ratio": ".85",
        "guidance_scale": 10,
        "negative_prompt": "low quality",
        "num_inference_steps": 10,
        "prompt": "human face",
        "remove_bg": true,
        "render": false,
        "resolution": 256,
        "seed": 3815040680,
        "temp": "no"
    }
}