Loading API documentation
Generate
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/trellis-2", {
input: {
image_url: "https://v3b.fal.media/files/b/0a86b60d/xkpao5B0uxmH0tmJm0HVL_2fe35ce1-fe44-475b-b582-6846a149537c.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);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/trellis-2", {
input: {
image_url: "https://v3b.fal.media/files/b/0a86b60d/xkpao5B0uxmH0tmJm0HVL_2fe35ce1-fe44-475b-b582-6846a149537c.png"
},
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/trellis-2", {
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/trellis-2", {
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.
seed integerRandom seed for reproducibility
resolution ResolutionEnumOutput resolution; higher is slower but more detailed Default value: "1024"
Possible enum values: 512, 1024, 1536
ss_guidance_strength floatHow closely the initial 3D structure follows the input image. Higher values produce more faithful but potentially noisier results. Default value: 7.5
ss_guidance_rescale floatDampens artifacts from high guidance in stage 1. Lower values allow stronger guidance effects, higher values stabilize the output. Default value: 0.7
ss_guidance_interval_start floatFraction of the denoising process at which classifier-free guidance starts for stage 1 (sparse structure). Guidance is only applied between interval_start and interval_end; outside this window the model runs unguided. Lower values apply guidance earlier. Default value: 0.6
ss_guidance_interval_end floatFraction of the denoising process at which classifier-free guidance ends for stage 1 (sparse structure). Must be >= ss_guidance_interval_start. Default value: 1
ss_sampling_steps integerNumber of denoising steps for the initial structure. More steps = slower but potentially higher quality. Default value: 12
ss_rescale_t floatControls noise schedule sharpness for structure generation. Higher values produce sharper transitions. Default value: 5
shape_slat_guidance_strength floatHow closely the detailed geometry follows the input image. Higher values add more detail but may introduce noise. Default value: 7.5
shape_slat_guidance_rescale floatDampens artifacts from high guidance in the shape stage. Increase if you see noisy geometry. Default value: 0.5
shape_slat_guidance_interval_start floatFraction of the denoising process at which classifier-free guidance starts for stage 2 (shape refinement). Guidance is only applied between interval_start and interval_end. Default value: 0.6
shape_slat_guidance_interval_end floatFraction of the denoising process at which classifier-free guidance ends for stage 2 (shape refinement). Must be >= shape_slat_guidance_interval_start. Default value: 1
shape_slat_sampling_steps integerNumber of denoising steps for shape refinement. More steps = slower but potentially smoother geometry. Default value: 12
shape_slat_rescale_t floatControls noise schedule sharpness for shape refinement. Higher values produce sharper geometric details. Default value: 3
tex_slat_guidance_strength floatHow closely the texture follows the input image colors. Higher values produce more vivid but potentially oversaturated textures. Default value: 1
tex_slat_guidance_rescale floatDampens artifacts from high guidance in the texture stage. Increase if textures look noisy or have color banding.
tex_slat_guidance_interval_start floatFraction of the denoising process at which classifier-free guidance starts for stage 3 (texture). Guidance is only applied between interval_start and interval_end. Default value: 0.6
tex_slat_guidance_interval_end floatFraction of the denoising process at which classifier-free guidance ends for stage 3 (texture). Must be >= tex_slat_guidance_interval_start. Default value: 0.9
tex_slat_sampling_steps integerNumber of denoising steps for texture generation. More steps = slower but potentially cleaner textures. Default value: 12
tex_slat_rescale_t floatControls noise schedule sharpness for texture generation. Higher values produce sharper texture details. Default value: 3
decimation_target integerTarget number of vertices in the final mesh. Lower values produce smaller files but less detail. 500k is good for most uses, reduce to 20k-50k for web/mobile. Default value: 500000
texture_size TextureSizeEnumResolution of the texture image baked onto the mesh. Higher values capture finer surface details but produce larger files. Default value: "2048"
Possible enum values: 1024, 2048, 4096
remesh booleanRebuild the mesh topology for cleaner triangles. Slower but usually produces better results for downstream use (animation, 3D printing, etc). Default value: true
remesh_band floatControls how far remeshing can move vertices from the original surface. Higher values allow more smoothing but may lose fine details. Default value: 1
remesh_project floatHow much to project remeshed vertices back onto the original surface. 0 = no projection (smoother), 1 = full projection (preserves detail).
uv_unwrap_angle_threshold_deg floatMaximum angle (in degrees) between adjacent face normals allowed within a single UV chart. Lower values produce more charts with less distortion; higher values produce fewer, larger charts with potentially more stretching. Default value: 90
uv_unwrap_refine_iterations integerNumber of local refinement passes during UV chart computation. Higher values produce cleaner chart boundaries at the cost of additional UV-unwrap time.
uv_unwrap_global_iterations integerNumber of global clustering passes during UV chart computation. More passes produce more balanced charts. Default value: 1
uv_unwrap_smooth_strength floatSmoothing strength applied to UV chart boundaries. Higher values reduce visible seams but may introduce UV distortion. Default value: 1
image_url string* requiredURL of the input image to convert to 3D
{
"resolution": 1024,
"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,
"remesh": true,
"remesh_band": 1,
"uv_unwrap_angle_threshold_deg": 90,
"uv_unwrap_global_iterations": 1,
"uv_unwrap_smooth_strength": 1,
"image_url": "https://v3b.fal.media/files/b/0a86b60d/xkpao5B0uxmH0tmJm0HVL_2fe35ce1-fe44-475b-b582-6846a149537c.png"
}Generated 3D GLB file
{
"model_glb": {
"url": "https://v3b.fal.media/files/b/0a86b61d/DNmTkiWHUQ8k-rG6aussB_trellis2_68d6300f70f34d23b69a912b5fe60487.glb"
}
}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.