MiniMax H3 open weights is live
Docs
Log-inSign-up

hitem3d/hi3d/image-to-3d

Generate 3D models from a single image with Hi3D.
Learn more about Hi3D Image to 3D
Inference
Commercial use
Partner
Schema
LLMs
PlaygroundAPIExamples

Table of contents

About

Generate a 3D model from a single image.

Uses the Sparc3D/Ultra3D-based HItem3D models. Set enable_texture=false for a geometry-only mesh (cheaper), and pick a model/resolution tier to trade off quality and cost.

1. Calling the API#

Install the client#

The client provides a convenient way to interact with the model API.

npm install --save @fal-ai/client

Setup your API Key#

Set FAL_KEY as an environment variable in your runtime.

export FAL_KEY="YOUR_API_KEY"

Submit a request#

The client API handles the API submit protocol. It will handle the request status updates and return the result when the request is completed.

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("hitem3d/hi3d/image-to-3d", {
  input: {
    image_url: "https://storage.googleapis.com/falserverless/example_inputs/dog.png"
  },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

2. Authentication#

The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.

API Key#

In case your app is running in an environment where you cannot set environment variables, you can set the API Key manually as a client configuration.
import { fal } from "@fal-ai/client";

fal.config({
  credentials: "YOUR_FAL_KEY"
});

3. Queue#

Submit a request#

The client API provides a convenient way to submit requests to the model.

import { fal } from "@fal-ai/client";

const { request_id } = await fal.queue.submit("hitem3d/hi3d/image-to-3d", {
  input: {
    image_url: "https://storage.googleapis.com/falserverless/example_inputs/dog.png"
  },
  webhookUrl: "https://optional.webhook.url/for/results",
});

Fetch request status#

You can fetch the status of a request to check if it is completed or still in progress.

import { fal } from "@fal-ai/client";

const status = await fal.queue.status("hitem3d/hi3d/image-to-3d", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
  logs: true,
});

Get the result#

Once the request is completed, you can fetch the result. See the Output Schema for the expected result format.

import { fal } from "@fal-ai/client";

const result = await fal.queue.result("hitem3d/hi3d/image-to-3d", {
  requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);

4. Files#

Some attributes in the API accept file URLs as input. Whenever that's the case you can pass your own URL or a Base64 data URI.

Data URI (base64)#

You can pass a Base64 data URI as a file input. The API will handle the file decoding for you. Keep in mind that for large files, this alternative although convenient can impact the request performance.

Hosted files (URL)#

You can also pass your own URLs as long as they are publicly accessible. Be aware that some hosts might block cross-site requests, rate-limit, or consider the request as a bot.

Uploading files#

We provide a convenient file storage that allows you to upload files and use them in your requests. You can upload files using the client API and use the returned URL in your requests.

import { fal } from "@fal-ai/client";

const file = new File(["Hello, World!"], "hello.txt", { type: "text/plain" });
const url = await fal.storage.upload(file);

Read more about file handling in our file upload guide.

5. Schema#

Input#

model ModelEnum

Model version used for generation. 'hitem3d*' are the general models; 'scene-portrait*' are tuned for portraits/characters. Default value: "hitem3dv2.1"

Possible enum values: hitem3dv1.5, hitem3dv2.0, hitem3dv2.1, scene-portraitv1.5, scene-portraitv2.0, scene-portraitv2.1

resolution Enum

Generation resolution. Supported values depend on the model: v1.5/v2.0 accept 512, 1024, 1536 and 1536pro; v2.1 accepts 1536fast and 1536pro; scene-portraitv1.5 accepts 1536; scene-portraitv2.0 accepts 1536pro; scene-portraitv2.1 accepts 1536profast and 1536pro. Defaults to the model's recommended resolution (1024 for v1.5/v2.0, the fast tier otherwise).

Possible enum values: 512, 1024, 1536, 1536pro, 1536fast, 1536profast

enable_texture boolean

Whether to generate textures in addition to geometry. When false, only the geometry mesh is generated (and billed). Default value: true

enable_pbr boolean

Generate PBR material maps together with the texture. Only supported (and billed) for v2.0/v2.1 models when enable_texture is true; ignored otherwise. Default value: true

face_count integer

Target face count of the generated model. When unset, the partner picks the recommended count for the resolution (e.g. 500k for 512, 1M for 1024, 2M for 1536).

export_format ExportFormatEnum

File format of the generated model. Default value: "glb"

Possible enum values: glb, obj, stl, fbx, usdz

enable_safety_checker boolean

If set to true, input images are checked for safety before processing. Default value: true

image_url string* required

URL of the input image. PNG, JPEG and WebP formats are supported, up to 20MB.

{
  "model": "hitem3dv2.1",
  "enable_texture": true,
  "enable_pbr": true,
  "export_format": "glb",
  "enable_safety_checker": true,
  "image_url": "https://storage.googleapis.com/falserverless/example_inputs/dog.png"
}

Output#

model_mesh File* required

Generated 3D model file.

thumbnail File

Preview image of the generated model, when available.

{
  "model_mesh": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  }
}

Other types#

File#

url string* required

The URL where the file can be downloaded from.

content_type string

The mime type of the file.

file_name string

The name of the file. It will be auto-generated if not provided.

file_size integer

The size of the file in bytes.

Related Models