fal-ai/hyper3d/rodin/v2.5/text-to-3d/fast

Rodin V2.5 by Hyper3D generates realistic and production ready 3D models from text or images. Do fast prototyping using the fast model.

Learn more about Rodin 2.5

Inference

Commercial use

Partner

Schema

LLMs

Playground API Examples

About

Process Text To 3D V25 Fast

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

Migrate to @fal-ai/client

The @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Please check the migration guide for more information.

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("fal-ai/hyper3d/rodin/v2.5/text-to-3d/fast", {
  input: {
    prompt: "A futuristic robot with sleek metallic design."
  },
  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"
});

Protect your API Key

When running code on the client-side (e.g. in a browser, mobile app or GUI applications), make sure to not expose your FAL_KEY. Instead, use a server-side proxy to make requests to the API. For more information, check out our server-side integration guide.

3. Queue#

Long-running requests

For long-running requests, such as training jobs or models with slower inference times, it is recommended to check the Queue status and rely on Webhooks instead of blocking while waiting for the result.

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("fal-ai/hyper3d/rodin/v2.5/text-to-3d/fast", {
  input: {
    prompt: "A futuristic robot with sleek metallic design."
  },
  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("fal-ai/hyper3d/rodin/v2.5/text-to-3d/fast", {
  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("fal-ai/hyper3d/rodin/v2.5/text-to-3d/fast", {
  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);

Auto uploads

The client will auto-upload the file for you if you pass a binary object (e.g. File, Data).

Read more about file handling in our file upload guide.

5. Schema#

Input#

prompt string* required

A textual prompt to guide model generation. Required for Text-to-3D mode.

tier TierEnum

Generation tier. Higher tiers produce more detailed meshes but cost more. See more info in the documentation. Selecting Gen-2.5-Minimum will automatically configure to a minimum mode, where 50K Triangle is selected, taking priority over quality_mesh_option. Default value: "Gen-2.5-Extreme-Low"

Possible enum values: Gen-2.5-Minimum, Gen-2.5-Extreme-Low, Gen-2.5-Low

seed integer

Seed value for randomization, ranging from 0 to 65535. Optional.

geometry_file_format GeometryFileFormatEnum

Format of the geometry file. Possible values: glb, usdz, fbx, obj, stl. Default is glb. Default value: "glb"

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

material MaterialEnum

Material type. PBR: physically-based materials with realistic lighting. Shaded: baked lighting with no PBR maps. All: both PBR and Shaded variants. None: geometry only with no textures. Default value: "All"

Possible enum values: PBR, Shaded, All, None

quality_mesh_option QualityMeshOptionEnum

Combined quality and mesh type selection. Quad = smooth surfaces, Triangle = detailed geometry. Maps to mesh_mode (Quad/Raw) and quality_override (face count) on the Hyper3D API. Valid face counts depend on the selected tier. Up to 1M Triangle is supported for tiers Minimum, Extreme-Low, Low. For fast endpoint, this limit is up to 20K, primarily for prototyping and testing. For generating higher quality meshes, use the standard endpoint. Auto option will choose the advised options for each tier:

Gen-2.5-Minimum: 20K Triangle
Gen-2.5-Extreme-Low: 20K Triangle
Gen-2.5-Low: 20K Triangle Default value: "Auto"

Possible enum values: Auto, 1K Quad, 4K Quad, 8K Quad, 18K Quad, 20K Quad, 2K Triangle, 4K Triangle, 8K Triangle, 10K Triangle, 20K Triangle

texture_mode Enum

Texture generation quality. When unset, the API picks a default appropriate for the tier.

Possible enum values: legacy, extreme-low, low, medium, high

enable_creative_mode boolean

If enabled, the generation will have enhanced generative robustness while ensuring output consistency. This corresponds to geometry_instruct_mode being equal to creative on the Hyper3D API.

hd_texture boolean

Enables enhanced texture post-processing for higher visual fidelity.

texture_delight boolean

Removes baked lighting/highlights from the generated textures.

is_micro boolean

Generate finer micro-scale geometric detail. Only effective with tier="Gen-2.5-Extreme-High".

TAPose boolean

Generate characters in T-pose or A-pose format, making them easier to rig and animate in 3D software.

bbox_condition RodinGen25BbboxField

This is a controlnet that controls the maximum sized of the generated model.

addons RodinGen25Addons

Optional add-ons

{
  "prompt": "A futuristic robot with sleek metallic design.",
  "tier": "Gen-2.5-Extreme-Low",
  "geometry_file_format": "glb",
  "material": "All",
  "quality_mesh_option": "Auto"
}

Output#

model_mesh File* required

Generated 3D object file.

model_meshes list<File>

Additional generated 3D object files returned by Hyper3D besides model_mesh.

seed integer* required

Seed value used for generation.

textures list<Image>* required

Generated textures for the 3D object.

{
  "model_mesh": {
    "url": "https://storage.googleapis.com/falserverless/model_tests/video_models/base_basic_shaded.glb"
  },
  "model_meshes": [
    {
      "url": "",
      "content_type": "image/png",
      "file_name": "z9RV14K95DvU.png",
      "file_size": 4404019
    }
  ],
  "textures": [
    {
      "url": "",
      "content_type": "image/png",
      "file_name": "z9RV14K95DvU.png",
      "file_size": 4404019,
      "width": 1024,
      "height": 1024
    }
  ]
}

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.

RodinGen25Addons#

high_pack boolean

Selecting HighPack generates 4K resolution texture instead of the default 2K. In Quad mode, the number of faces becomes ~16× the count set in the quality parameter.

RodinGen25BbboxField#

width integer

Width (x axis) dimension for the bounding box constraint.

height integer

Height (y axis) dimension for the bounding box constraint.

length integer

Length (z axis) dimension for the bounding box constraint.

Image#

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.

width integer

The width of the image in pixels.

height integer

The height of the image in pixels.

fal-ai/hyper3d/rodin/v2.5/text-to-3d/fast

Table of contents

1. Calling the API

2. Authentication

3. Queue

4. Files

5. Schema

About

1. Calling the API#

Install the client#

Migrate to @fal-ai/client

Setup your API Key#

Submit a request#

2. Authentication#

API Key#

Protect your API Key

3. Queue#

Long-running requests

Submit a request#

Fetch request status#

Get the result#

4. Files#

Data URI (base64)#

Hosted files (URL)#

Uploading files#

Auto uploads

5. Schema#

Input#

Output#

Other types#

File#

RodinGen25Addons#

RodinGen25BbboxField#

Image#

Related Models