Loading API documentation
Text-to-3D generation using Rodin Gen-2.5
The client provides a convenient way to interact with the model API.
npm install --save @fal-ai/clientThe @fal-ai/serverless-client package has been deprecated in favor of @fal-ai/client. Install the new package and update your imports — see client setup.
Set FAL_KEY as an environment variable in your runtime.
export FAL_KEY="YOUR_API_KEY"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", {
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);The API uses an API Key for authentication. It is recommended you set the FAL_KEY environment variable in your runtime when possible.
import { fal } from "@fal-ai/client";
fal.config({
credentials: "YOUR_FAL_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.
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", {
input: {
prompt: "A futuristic robot with sleek metallic design."
},
webhookUrl: "https://optional.webhook.url/for/results",
});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", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b",
logs: true,
});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", {
requestId: "764cabcf-b745-4b3e-ae38-1200304cf45b"
});
console.log(result.data);
console.log(result.requestId);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.
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.
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.
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);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.
prompt string* requiredA textual prompt to guide model generation. Required for Text-to-3D mode.
tier TierEnumGeneration tier. Higher tiers produce more detailed meshes. 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-High"
Possible enum values: Gen-2.5-Minimum, Gen-2.5-Extreme-Low, Gen-2.5-Low, Gen-2.5-Medium, Gen-2.5-High, Gen-2.5-Extreme-High
seed integerSeed value for randomization, ranging from 0 to 65535. Optional.
geometry_file_format GeometryFileFormatEnumFormat 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 MaterialEnumMaterial 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 QualityMeshOptionEnumCombined 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 Extreme-Low, Low, and Medium. Up to 2M Triangle (as low as 20K Triangle) is supported for tiers High and Extreme-High. Auto option will choose the advised options for each tier:
"Auto"Possible enum values: Auto, 4K Quad, 8K Quad, 18K Quad, 50K Quad, 100K Quad, 200K Quad, 2K Triangle, 20K Triangle, 50K Triangle, 150K Triangle, 500K Triangle, 1M Triangle, 2M Triangle
texture_mode EnumTexture 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 booleanIf 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 booleanEnables enhanced texture post-processing for higher visual fidelity.
texture_delight booleanRemoves baked lighting/highlights from the generated textures.
is_micro booleanGenerate finer micro-scale geometric detail. Only effective with tier="Gen-2.5-Extreme-High".
TAPose booleanGenerate characters in T-pose or A-pose format, making them easier to rig and animate in 3D software.
This is a controlnet that controls the maximum sized of the generated model.
Optional add-ons
enable_safety_checker booleanAuthorized callers may set false to request relaxed screening. Default value: true
{
"prompt": "A futuristic robot with sleek metallic design.",
"tier": "Gen-2.5-High",
"geometry_file_format": "glb",
"material": "All",
"quality_mesh_option": "Auto",
"enable_safety_checker": true
}Generated 3D object file.
Additional generated 3D object files returned by Hyper3D besides model_mesh.
seed integer* requiredSeed value used for generation.
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
}
]
}width integerWidth (x axis) dimension for the bounding box constraint.
height integerHeight (y axis) dimension for the bounding box constraint.
length integerLength (z axis) dimension for the bounding box constraint.
high_pack booleanSelecting 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.
url string* requiredThe URL where the file can be downloaded from.
content_type stringThe mime type of the file.
file_name stringThe name of the file. It will be auto-generated if not provided.
file_size integerThe size of the file in bytes.
width integerThe width of the image in pixels.
height integerThe height of the image in pixels.
url string* requiredThe URL where the file can be downloaded from.
content_type stringThe mime type of the file.
file_name stringThe name of the file. It will be auto-generated if not provided.
file_size integerThe size of the file in bytes.