TRELLIS.2 image-to-3D model that turns a reference image into a textured GLB asset with resolution, seed, mesh, texture, and export controls.
Microsoft3D GenerationNative InferenceNewTRELLIS.2 image-to-3D model that turns a reference image into a textured GLB asset with resolution, seed, mesh, texture, and export controls.
trellis-2-4bPOST /v1/3d/generationsLive pay-as-you-go rates from the EmpirioLabs catalog. You are billed only for what you use, with no monthly minimum.
TRELLIS.2 4B runs through POST /v1/3d/generations. The request returns a job_id right away; poll GET /v1/jobs/{job_id} until the job completes and read the output URLs from the result. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/3d/generations \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "trellis-2-4b",
"prompt": "Describe what you want TRELLIS.2 4B to generate."
}'curl https://api.empiriolabs.ai/v1/jobs/JOB_ID \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY"import requests
response = requests.post(
"https://api.empiriolabs.ai/v1/3d/generations",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
json={
"model": "trellis-2-4b",
"prompt": "Describe what you want TRELLIS.2 4B to generate.",
},
)
job = response.json()
# Generation runs as an async job. Poll until it completes.
import time
while True:
status = requests.get(
f"https://api.empiriolabs.ai/v1/jobs/{job['job_id']}",
headers={"Authorization": "Bearer YOUR_EMPIRIOLABS_API_KEY"},
).json()
if status.get("status") in ("completed", "failed"):
print(status)
break
time.sleep(5)Request parameters supported by the TRELLIS.2 4B API on EmpirioLabs. Defaults apply when a field is omitted.
| Parameter | Type | Default | Range / values | Description |
|---|---|---|---|---|
| image | image | - | - | Reference image URL, data URI, or uploaded image object. |
| resolution | enum | 1024 | 512, 1024, 1536 | Voxel grid resolution. Higher values are slower and more detailed. |
| pipeline_type | enum | 1024_cascade | 512, 1024_cascade, 1536_cascade | Explicit TRELLIS pipeline. Leave on 1024 cascade unless you need the 512 or 1536 path. |
| seed | integer | 42 | 0 to 2147483647 | Random seed for reproducible generations. |
| preprocess_image | boolean | true | - | Remove background and normalize the reference image before generation. |
| max_num_tokens | integer | 49152 | 1024 to 131072 | Maximum sparse tokens used for cascade generation. |
| ss_sampling_steps | integer | 12 | 1 to 64 | Sampler steps for sparse structure generation. |
| ss_guidance_strength | number | 7.5 | 0 to 20 | Guidance strength for sparse structure generation. |
| ss_guidance_rescale | number | 0.7 | 0 to 2 | Guidance rescale for sparse structure generation. |
| ss_guidance_interval_start | number | 0.6 | 0 to 1 | Start of the sparse-structure guidance interval. |
| ss_guidance_interval_end | number | 1 | 0 to 1 | End of the sparse-structure guidance interval. |
| ss_rescale_t | number | 5 | 0 to 20 | Rescale temperature for sparse structure generation. |
| shape_slat_sampling_steps | integer | 12 | 1 to 64 | Sampler steps for shape structured latent generation. |
| shape_slat_guidance_strength | number | 7.5 | 0 to 20 | Guidance strength for shape structured latent generation. |
Supports image URL or upload, 512/1024/1536 resolution, seed, pipeline type, sampler guidance/interval/rescale controls, texture size, mesh decimation, remeshing, UV unwrap tuning, and URL or base64 output. Billing is per generated 3D asset.
On EmpirioLabs, TRELLIS.2 4B is billed pay as you go: 512 asset $0.025 (was $0.25) per request; 1024 asset $0.249 (was $0.30) per request; 1536 asset $0.499 per request. The live rate card on this page always matches what the API charges.
TRELLIS.2 4B is served through POST /v1/3d/generations on api.empiriolabs.ai with standard bearer-token authentication.
Yes. The EmpirioLabs playground runs TRELLIS.2 4B in the browser with the same parameters the API exposes, so you can test prompts before writing code.
Create an EmpirioLabs account, then generate a key under API Keys in the dashboard. Billing is pay-as-you-go credits, so you only pay for the requests you make.
Explore our models, or contact us about business inquiries, custom deployments, or anything else.