fal-ai/trellis-2-lora

Run inference on LoRA adapters for TRELLIS.2 model

Inference

Commercial use

Schema

LLMs

Playground API Examples

About

Inference

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/trellis-2-lora", {
  input: {
    image_url: ""
  },
  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/trellis-2-lora", {
  input: {
    image_url: ""
  },
  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/trellis-2-lora", {
  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/trellis-2-lora", {
  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#

image_url string* required

URL of the input image to convert to a 3D model.

sparse_structure_lora_url string

Optional safetensors LoRA checkpoint trained for the sparse structure denoiser.

geometry_lora_url string

Optional safetensors LoRA checkpoint trained for the geometry denoiser.

texture_lora_url string

Optional safetensors LoRA checkpoint trained for the texture denoiser.

seed integer

Random seed for reproducible generation.

resolution ResolutionEnum

Generation resolution. Must match the resolution the provided LoRA adapters were trained at (1024 runs the cascade pipeline). Default value: "512"

Possible enum values: 512, 1024

ss_guidance_strength float

Classifier-free guidance strength for the sparse-structure stage. Default value: 7.5

ss_guidance_rescale float

Guidance rescale for the sparse-structure stage; higher stabilizes output. Default value: 0.7

ss_guidance_interval_start float

Denoising fraction at which guidance starts for the sparse-structure stage. Default value: 0.6

ss_guidance_interval_end float

Denoising fraction at which guidance ends for the sparse-structure stage. Must be >= ss_guidance_interval_start. Default value: 1

ss_sampling_steps integer

Number of denoising steps for the sparse-structure stage. Default value: 12

ss_rescale_t float

Noise-schedule sharpness for the sparse-structure stage. Default value: 5

shape_slat_guidance_strength float

Classifier-free guidance strength for the shape stage. Default value: 7.5

shape_slat_guidance_rescale float

Guidance rescale for the shape stage; increase if geometry looks noisy. Default value: 0.5

shape_slat_guidance_interval_start float

Denoising fraction at which guidance starts for the shape stage. Default value: 0.6

shape_slat_guidance_interval_end float

Denoising fraction at which guidance ends for the shape stage. Must be >= shape_slat_guidance_interval_start. Default value: 1

shape_slat_sampling_steps integer

Number of denoising steps for the shape stage. Default value: 12

shape_slat_rescale_t float

Noise-schedule sharpness for the shape stage. Default value: 3

tex_slat_guidance_strength float

Classifier-free guidance strength for the texture stage. Default value: 1

tex_slat_guidance_rescale float

Guidance rescale for the texture stage; increase if textures look noisy.

tex_slat_guidance_interval_start float

Denoising fraction at which guidance starts for the texture stage. Default value: 0.6

tex_slat_guidance_interval_end float

Denoising fraction at which guidance ends for the texture stage. Must be >= tex_slat_guidance_interval_start. Default value: 0.9

tex_slat_sampling_steps integer

Number of denoising steps for the texture stage. Default value: 12

tex_slat_rescale_t float

Noise-schedule sharpness for the texture stage. Default value: 3

decimation_target integer

Target vertex count for the exported GLB. Default value: 500000

texture_size TextureSizeEnum

Texture resolution baked into the exported GLB. Default value: "2048"

Possible enum values: 1024, 2048, 4096

{
  "image_url": "",
  "resolution": 512,
  "ss_guidance_strength": 7.5,
  "ss_guidance_rescale": 0.7,
  "ss_guidance_interval_start": 0.6,
  "ss_guidance_interval_end": 1,
  "ss_sampling_steps": 12,
  "ss_rescale_t": 5,
  "shape_slat_guidance_strength": 7.5,
  "shape_slat_guidance_rescale": 0.5,
  "shape_slat_guidance_interval_start": 0.6,
  "shape_slat_guidance_interval_end": 1,
  "shape_slat_sampling_steps": 12,
  "shape_slat_rescale_t": 3,
  "tex_slat_guidance_strength": 1,
  "tex_slat_guidance_interval_start": 0.6,
  "tex_slat_guidance_interval_end": 0.9,
  "tex_slat_sampling_steps": 12,
  "tex_slat_rescale_t": 3,
  "decimation_target": 500000,
  "texture_size": 2048
}

Output#

model_glb File* required

Generated 3D GLB file.

seed integer* required

Seed used for generation.

resolution integer* required

Generation resolution used.

sparse_structure_lora_url string

Sparse-structure LoRA checkpoint applied for this generation, if any.

geometry_lora_url string

Geometry LoRA checkpoint applied for this generation, if any.

texture_lora_url string

Texture LoRA checkpoint applied for this generation, if any.

decimation_target integer* required

Target vertex count used for the exported GLB.

texture_size integer* required

Texture resolution baked into the exported GLB.

{
  "model_glb": {
    "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.

fal-ai/trellis-2-lora

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#