Trellis 2

Integrar

ID dal model trellis-2

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/trellis-2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/trellis-2?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/trellis-2", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/rm/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.com/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "trellis-2",
  "input": {
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }
}

Cloma il model Trellis 2 (trellis-2) tras la Doitong API. Documentaziun per agents: https://doitong.com/rm/developers/models/trellis-2.md

POST https://api.doitong.com/v1/run/trellis-2?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
}

Sche il status da la resposta è "queued" u "running", fa polling GET https://api.doitong.com/v1/requests/REQUEST_ID?wait=20 fin ch'el è "succeeded"; las datotecas èn en outputs[].url. POST https://api.doitong.com/v1/quote/trellis-2 cun il medem body returna il pretsch exact avant l'execuziun.

Questa dumonda: $0,30 300 credits API Lantschar sin questa pagina

Obtegna ina clav API

Microsoft Maletg a 3D #image-to-3d

Transforma ina singula imagina en ina mesh 3D GLB cun textur e configuraziuns regulablas per structura, furma, textur e UV

OpenAPI Markdown

Microsoft · 3D

Tes emprim resultat vegn qua

Construis ina dumonda sutvart e l'exequescha cun tia clav API. Outputs vegnan copiads en nossa memorisaziun, conservads per adina u 7 dis gratuitamain.

Construir ina dumonda

Ils controls vegnan generads dal schema dal model. Il code e il pretsch s'actualiseschan durant che ti als midas.

image •obligatori image_url

Trametta in datoteca u

URL che mussa sin il maletg da funtauna per la conversiun 3D.

resolution standard 1024

Resoluziun dal output; augmentar ella agiunta detagls, ma dovra dapli temp.

Avanzà texture_size · ss_guidance_strength · ss_guidance_rescale · ss_guidance_interval_start · ss_guidance_interval_end · ss_sampling_steps · ss_rescale_t · shape_slat_guidance_strength · shape_slat_guidance_rescale · shape_slat_guidance_interval_start · shape_slat_guidance_interval_end · shape_slat_sampling_steps · shape_slat_rescale_t · tex_slat_guidance_strength · tex_slat_guidance_rescale · tex_slat_guidance_interval_start · tex_slat_guidance_interval_end · tex_slat_sampling_steps · tex_slat_rescale_t · decimation_target · remesh_band · remesh_project · uv_unwrap_angle_threshold_deg · uv_unwrap_refine_iterations · uv_unwrap_global_iterations · uv_unwrap_smooth_strength · seed · remesh

texture_size standard 2048

Resoluziun da la textura dal mesh per il baking. Detagl da surfatscha pli fin dat datotecas pli grondas sch'igl vegn augmentada questa resoluziun.

ss_guidance_strength standard 7.5

Controlla la fidelitad da la structura 3D iniziala: augmentar ella favurisescha ina concordanza pli gronda cun il maletg input, cun il ristg da dapli ramur.

ss_guidance_rescale standard 0.7

Controlla ils artifacts da guida dal stadi 1, cun effects da guida pli ferms tar configuraziuns bassas e in output pli stabil tar configuraziuns autas.

ss_guidance_interval_start standard 0.6

Limita d'inizi da la fanestra da guidance senza classificader en la fasa 1 (structura sparsa), exprimida sco fracziun da reducziun dal ramur. Configuraziuns pli bassas cumenzan la guidance pli baud; mo l'interval tranter interval_start e interval_end utilisescha guidance, entant che l'elavuraziun è senza guidance en il rest.

ss_guidance_interval_end standard 1

Limita da guidance per la fasa 1 (structura sparsa): tscherna ina valur almain uschè gronda sco ss_guidance_interval_start. La valur inditgescha la fracziun da reducziun dal ramur cuntanschida cura che la guidance senza classificader sa fermescha.

ss_sampling_steps standard 12

Dumber da pass da denoising da la structura iniziala: ils pussibels avantatgs da qualitad da pass supplementars vegnan cun in processament pli lent.

ss_rescale_t standard 5

Definescha la nettezza da la transiziun tras il noise schedule da la generaziun da la structura: augmentar questa valur fa las transiziuns pli nettas.

shape_slat_guidance_strength standard 7.5

Controlla la fidelitad da la geometria detagliada: ina aderenza pli gronda al maletg input dat dapli detagl, cun il ristg da ramur supplementara.

shape_slat_guidance_rescale standard 0.5

Augmenta questa configuraziun sche la geometria para ramurusa: ella reducescha ils artifacts chaschunads da la guida ferma durant il stadi da la furma.

shape_slat_guidance_interval_start standard 0.6

Punct d'activaziun da la guidance senza classificader per la raffinaziun da la furma en la fasa 2. Exprimì sco fracziun dal progress da reducziun dal ramur, fixescha el interval_start; la guidance funcziuna mo en la fanestra limitada da interval_start e interval_end.

shape_slat_guidance_interval_end standard 1

Limita da guidance per la fasa 2 (raffinaziun da la furma): tscherna ina valur almain uschè gronda sco shape_slat_guidance_interval_start. La valur inditgescha la fracziun da reducziun dal ramur cuntanschida cura che la guidance senza classificader sa fermescha.

shape_slat_sampling_steps standard 12

Dumber da pass da denoising per il meglierament da la furma: ina geometria eventualmain pli glischa custa spertadad sch'i vegnan duvrads pass supplementars.

shape_slat_rescale_t standard 3

Definescha la nettezza dal detagl geometric tras il noise schedule dal meglierament da la furma; augmentar questa valur dat detagls pli nets.

tex_slat_guidance_strength standard 1

Controlla la fidelitad da la colur da la textura: ina aderenza pli gronda a las colurs dal maletg input tar configuraziuns autas augmenta la vivacitad, ma po chaschunar sursaturaziun.

tex_slat_guidance_rescale standard 0

Augmenta questa configuraziun per tractar texturas ramurusas u bandas da colur: ella reducescha ils artifacts chaschunads da la guida ferma durant il stadi da la textura.

tex_slat_guidance_interval_start standard 0.6

Punct d'activaziun da la guidance senza classificader per la generaziun da textura en la fasa 3. Exprimì sco fracziun dal progress da reducziun dal ramur, fixescha el interval_start; la guidance funcziuna mo en la fanestra limitada da interval_start e interval_end.

tex_slat_guidance_interval_end standard 0.9

Limita da guidance per la fasa 3 (textura): tscherna ina valur almain uschè gronda sco tex_slat_guidance_interval_start. La valur inditgescha la fracziun da reducziun dal ramur cuntanschida cura che la guidance senza classificader sa fermescha.

tex_slat_sampling_steps standard 12

Dumber da pass da denoising utilisads per generar texturas. Augmentar il dumber da pass dovra dapli temp, ma po producir texturas pli nettas.

tex_slat_rescale_t standard 3

Definescha la nettezza dal detagl da la textura tras il noise schedule da la generaziun da texturas; augmentar questa valur dat detagls pli nets.

decimation_target standard 500000

Finamira dal dumber da vertizels da la rait, cun 500k recumandà per l'ultilisaziun generala e 20k–50k per web/mobile. La reducziun da la finamira baratta detagls da la rait cunter datotecas pli pitschnas.

remesh_band standard 1

Margine da moviment per il remeshing: ina glisada supplementara po sacrificar detagls fins sch'esta valur vegn augmentada. La configuraziun limitescha il spustament dals vertizels en relaziun cun la surfatscha originala.

remesh_project standard 0

Forza da la proiecziun per turnar ils vertizels remeshed a la surfatscha originala: 1 mantegna ils detagls tras proiecziun cumpletta, entant che 0 deactivescha la proiecziun per in resultat pli lom.

uv_unwrap_angle_threshold_deg standard 90

Limita d'angul dals charts UV en grads, che limitescha quant fitg che las normallas da fatschas vischinas pon sa differenziar entaifer in chart. Ina limita pli auta preferescha damain charts pli gronds, cun il ristg da stender; ina limita pli bassa preferescha dapli charts e damain distorsiun.

uv_unwrap_refine_iterations standard 0

Dumber da pass da raffinaziun locals utilisads per calcular charts UV.

uv_unwrap_global_iterations standard 1

L'equiliber dal chart UV po vegnir meglierà augmentond quest dumber da pass da clustering globals utilisads per calcular ils charts.

uv_unwrap_smooth_strength standard 1

Adattescha quant ferm che ils urs dals charts UV vegnan glisads; configuraziuns pli autas reduceschan las giunturas visiblas, ma cun il ristg da distorsiun UV.

seed

Seed utilisà per ina generaziun casuala reproducibla.

POST /run/trellis-2?wait=20 calculaziun → $0,30

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/trellis-2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.com/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/trellis-2?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.com/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/trellis-2", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "trellis-2",
      "input": {
        "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      },
      "wait_seconds": 20
    }
  }
}

Executar questa dumonda

Clav API

Tia clav resta en quest browser: ella vegn tramessa mo al Doitong API e memorisada (localStorage) mo sch'ella scheccas Tiar a memoria. Memorisar en quest navigatur Obtegnair ina clav API

Davart Trellis 2

Construiescha in asset 3D d'ina imagina (`image_url`) e returnescha ina datoteca GLB. `resolution` è 512, 1024 u 1536; `texture_size` è 1024, 2048 u 4096. Mintgina da las trais staziuns (structura, furma, textur) ha controlls agens per guidance e pass da sampling. `decimation_target` definescha il dumber da vertizels da la mesh (5,000 to 2,000,000); remeshing e deballagi UV èn disponibels.

Parameters

Invia u il num canonic u il num nativ, betg omaduas. Nums canonics

NumTip StandardPermess Descripziun

seedopziunal

Tipinteger | null

Seed utilisà per ina generaziun casuala reproducibla.

resolutionopziunal

Tipenum

Standard1024

51210241536

Resoluziun dal output; augmentar ella agiunta detagls, ma dovra dapli temp.

ss_guidance_strengthopziunal

Tipnumber

Standard7.5

0 – 10

Controlla la fidelitad da la structura 3D iniziala: augmentar ella favurisescha ina concordanza pli gronda cun il maletg input, cun il ristg da dapli ramur.

ss_guidance_rescaleopziunal

Tipnumber

Standard0.7

0 – 1

Controlla ils artifacts da guida dal stadi 1, cun effects da guida pli ferms tar configuraziuns bassas e in output pli stabil tar configuraziuns autas.

ss_guidance_interval_startopziunal

Tipnumber

Standard0.6

0 – 1

ss_guidance_interval_endopziunal

Tipnumber

Standard1

0 – 1

ss_sampling_stepsopziunal

Tipinteger

Standard12

1 – 50

Dumber da pass da denoising da la structura iniziala: ils pussibels avantatgs da qualitad da pass supplementars vegnan cun in processament pli lent.

ss_rescale_topziunal

Tipnumber

Standard5

1 – 6

Definescha la nettezza da la transiziun tras il noise schedule da la generaziun da la structura: augmentar questa valur fa las transiziuns pli nettas.

shape_slat_guidance_strengthopziunal

Tipnumber

Standard7.5

0 – 10

Controlla la fidelitad da la geometria detagliada: ina aderenza pli gronda al maletg input dat dapli detagl, cun il ristg da ramur supplementara.

shape_slat_guidance_rescaleopziunal

Tipnumber

Standard0.5

0 – 1

Augmenta questa configuraziun sche la geometria para ramurusa: ella reducescha ils artifacts chaschunads da la guida ferma durant il stadi da la furma.

shape_slat_guidance_interval_startopziunal

Tipnumber

Standard0.6

0 – 1

shape_slat_guidance_interval_endopziunal

Tipnumber

Standard1

0 – 1

shape_slat_sampling_stepsopziunal

Tipinteger

Standard12

1 – 50

Dumber da pass da denoising per il meglierament da la furma: ina geometria eventualmain pli glischa custa spertadad sch'i vegnan duvrads pass supplementars.

shape_slat_rescale_topziunal

Tipnumber

Standard3

1 – 6

Definescha la nettezza dal detagl geometric tras il noise schedule dal meglierament da la furma; augmentar questa valur dat detagls pli nets.

tex_slat_guidance_strengthopziunal

Tipnumber

Standard1

0 – 10

Controlla la fidelitad da la colur da la textura: ina aderenza pli gronda a las colurs dal maletg input tar configuraziuns autas augmenta la vivacitad, ma po chaschunar sursaturaziun.

tex_slat_guidance_rescaleopziunal

Tipnumber

Standard0

0 – 1

Augmenta questa configuraziun per tractar texturas ramurusas u bandas da colur: ella reducescha ils artifacts chaschunads da la guida ferma durant il stadi da la textura.

tex_slat_guidance_interval_startopziunal

Tipnumber

Standard0.6

0 – 1

tex_slat_guidance_interval_endopziunal

Tipnumber

Standard0.9

0 – 1

tex_slat_sampling_stepsopziunal

Tipinteger

Standard12

1 – 50

Dumber da pass da denoising utilisads per generar texturas. Augmentar il dumber da pass dovra dapli temp, ma po producir texturas pli nettas.

tex_slat_rescale_topziunal

Tipnumber

Standard3

1 – 6

Definescha la nettezza dal detagl da la textura tras il noise schedule da la generaziun da texturas; augmentar questa valur dat detagls pli nets.

decimation_targetopziunal

Tipinteger

Standard500000

5 000 – 2 000 000

texture_sizeopziunal

Tipenum

Standard2048

102420484096

Resoluziun da la textura dal mesh per il baking. Detagl da surfatscha pli fin dat datotecas pli grondas sch'igl vegn augmentada questa resoluziun.

remeshopziunal

Tipboolean

Standardtrue

Reconstrucziun da la topologia che crea trianguls da la rait pli nets, normalmain meglierond l'adattaziun a diever posteriur sco animaziun u stampa 3D, a cust da l'elavuraziun pli lenta.

remesh_bandopziunal

Tipnumber

Standard1

0 – 4

remesh_projectopziunal

Tipnumber

Standard0

0 – 1

Forza da la proiecziun per turnar ils vertizels remeshed a la surfatscha originala: 1 mantegna ils detagls tras proiecziun cumpletta, entant che 0 deactivescha la proiecziun per in resultat pli lom.

uv_unwrap_angle_threshold_degopziunal

Tipnumber

Standard90

0 – 180

uv_unwrap_refine_iterationsopziunal

Tipinteger

Standard0

0 – 10

Dumber da pass da raffinaziun locals utilisads per calcular charts UV.

uv_unwrap_global_iterationsopziunal

Tipinteger

Standard1

1 – 10

L'equiliber dal chart UV po vegnir meglierà augmentond quest dumber da pass da clustering globals utilisads per calcular ils charts.

uv_unwrap_smooth_strengthopziunal

Tipnumber

Standard1

0 – 10

Adattescha quant ferm che ils urs dals charts UV vegnan glisads; configuraziuns pli autas reduceschan las giunturas visiblas, ma cun il ristg da distorsiun UV.

image_urlobligatori image

Tipurl · image

URL che mussa sin il maletg da funtauna per la conversiun 3D.

obligatori Num canonic, er acceptà

Ils parameters da datotecas acceptan ina URL publica https://, ina URI data: fin a 10 MB u il file_url d'ina chargiada. Datotecas

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "trellis-2",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 300,
    "usd": "0.30",
    "charged": 300,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "output": {
    "model_glb": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_name": "0-output.jpeg",
      "file_size": 1843200
    }
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

Tias datotecas, tia decisiunMintga outputs[].url è ina copia en nossa memorisaziun: conservada per adina (pajà per GB-mes) u 7 dis gratuitamain, tenor la configuraziun dal conto u ?storage=.

La medema structura per mintga modeltype, url, content_type, width, height e duration, tant per maletgs sco per video e audio. output è l'object da resultat dal model sez.

Champs da l'output

model_glb: object {url, content_type, file_name, file_size}Model 3D generà en format GLB.

Dapli models: Maletg a 3D

Per agents AI: questa pagina sco Markdown è disponibla sut https://doitong.com/rm/developers/models/trellis-2.md. Tut ils models e las guidas: https://doitong.com/developers/llms.txt

Tes emprim resultat vegn qua

Construir ina dumonda

Executar questa dumonda

Davart Trellis 2

Parameters

Output

Autras variantes Trellis 2

Trellis 2 · Retexture Variantes: 2

Dapli models: Maletg a 3D

Trellis Variantes: 2

Trellis · Multi Variantes: 2

TRELLIS.2 LoRA Inference

Hi3D Image to 3D Variantes: 6