fal Assets is now live!
Docs
Log-inSign-up

fal-ai/trellis-2-lora-trainer

Train LoRA adapters for TRELLIS.2 model
Training
Commercial use
Schema
LLMs
PlaygroundAPI

Table of contents

About

Lora

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("fal-ai/trellis-2-lora-trainer", {
  input: {
    data_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"
});

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("fal-ai/trellis-2-lora-trainer", {
  input: {
    data_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-trainer", {
  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-trainer", {
  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#

data_url string* required

URL to a .zip archive containing raw 3D assets or a TRELLIS.2 preprocessed dataset zip returned by the data_preprocessing endpoint.

denoisers list<Enum>

TRELLIS.2 denoisers to fine-tune. One LoRA adapter is trained per entry, and all selected denoisers are trained in parallel from the same preprocessed dataset. Provide 1-3 unique values out of sparse_structure, geometry, and texture.

resolution ResolutionEnum

Training resolution. Must match the resolution the dataset is preprocessed at. Sparse-structure training uses the same config at both resolutions; geometry and texture have dedicated 512/1024 configs. Default value: "512"

Possible enum values: 512, 1024

rank RankEnum

LoRA rank. Higher values increase adapter capacity. Default value: "32"

Possible enum values: 16, 32, 64

learning_rate float

Learning rate for LoRA optimization. Default value: 0.0001

training_steps integer

Number of training steps. Default value: 1000

{
  "data_url": "",
  "resolution": 512,
  "rank": 32,
  "learning_rate": 0.0001,
  "training_steps": 1000
}

Output#

adapters list<LoraAdapterResult>* required

Trained LoRA adapters, one per denoiser that completed successfully. Use each adapter's file in the matching trellis-2-lora inference field.

failed list<LoraTrainingFailure>

Denoisers whose training did not complete. Empty when every requested denoiser succeeded.

preprocessed_data_file File* required

Reusable TRELLIS.2 preprocessed dataset zip used for training.

{
  "adapters": [
    {
      "denoiser": "sparse_structure",
      "resolution": 512,
      "lora_file": {
        "url": "",
        "content_type": "image/png",
        "file_name": "z9RV14K95DvU.png",
        "file_size": 4404019
      },
      "rank": 16
    }
  ],
  "failed": [
    {
      "denoiser": "sparse_structure",
      "error": ""
    }
  ],
  "preprocessed_data_file": {
    "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.

LoraTrainingFailure#

denoiser DenoiserEnum* required

TRELLIS.2 denoiser whose training did not complete.

Possible enum values: sparse_structure, geometry, texture

error string* required

Reason the training did not complete.

LoraAdapterResult#

denoiser DenoiserEnum* required

TRELLIS.2 denoiser this LoRA adapter was trained for: sparse_structure, geometry, or texture.

Possible enum values: sparse_structure, geometry, texture

resolution ResolutionEnum* required

Resolution this LoRA adapter was trained at. Use the same resolution in trellis-2-lora inference.

Possible enum values: 512, 1024

lora_file File* required

Trained TRELLIS.2 LoRA adapter.

rank RankEnum* required

LoRA rank used for training.

Possible enum values: 16, 32, 64

training_steps integer* required

Number of training steps run.

learning_rate float* required

Learning rate used for LoRA optimization.