TRELLIS.2 LoRA Inference

Unganisha

Kitambulisho cha modeli trellis-2-lora

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/trellis-2-lora?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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/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-lora?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.ru/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-lora", 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/sw/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

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

Piga modeli ya TRELLIS.2 LoRA Inference (trellis-2-lora) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/trellis-2-lora.md

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

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

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.ru/v1/quote/trellis-2-lora yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Ombi hili: $ 0.25 salio za API 250 · ≈ ₽ 26.37 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Microsoft Picha hadi 3D

Trellis 2 ya picha-hadi-3D inayoweza kutumia adapta maalum za LoRA kwa muundo, jiometri na tekstura

OpenAPI Markdown

Microsoft · 3D

Tokeo lako la kwanza linaonekana hapa

Unda ombi hapa chini na uliendeshe kwa ufunguo wako wa API. Matokeo yanakiliwa kwenye hifadhi yetu, yakihifadhiwa milele au 7 siku bila malipo.

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

image •inahitajika image_url

Dondosha faili, au

URL ya picha chanzo ya kugeuza kuwa modeli ya 3D.

resolution chaguomsingi 512

Mwonekano wa uzalishaji, ambapo 1024 huchagua pipeline ya cascade. Chagua mwonekano uliotumika kufunza adapta za LoRA ulizotoa; lazima zilingane.

Ya kina texture_lora_url · texture_size · sparse_structure_lora_url · geometry_lora_url · 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 · seed · enable_safety_checker

texture_lora_url

Checkpoint ya hiari ya LoRA katika muundo wa safetensors, iliyofunzwa mahsusi kwa denoiser ya umbile.

texture_size chaguomsingi 2048

Mwonekano wa maumbo yaliyookwa katika uhamishaji wa GLB.

sparse_structure_lora_url

Checkpoint ya hiari ya LoRA katika muundo wa safetensors, iliyofunzwa mahsusi kwa denoiser ya muundo adimu.

geometry_lora_url

Checkpoint ya hiari ya LoRA katika muundo wa safetensors, iliyofunzwa mahsusi kwa denoiser ya jiometri.

ss_guidance_strength chaguomsingi 7.5

Nguvu ya mwongozo wa classifier-free wakati wa uzalishaji wa muundo adimu.

ss_guidance_rescale chaguomsingi 0.7

Urekebishaji wa mwongozo wakati wa uzalishaji wa muundo adimu. Thamani kubwa hufanya tokeo liwe thabiti zaidi.

ss_guidance_interval_start chaguomsingi 0.6

Sehemu ya maendeleo ya kuondoa kelele ambapo mwongozo wa muundo adimu huanza.

ss_guidance_interval_end chaguomsingi 1

Tumia sehemu ya kuondoa kelele iliyo kwenye au juu ya `ss_guidance_interval_start` kubainisha wakati mwongozo wa muundo adimu unasitishwa.

ss_sampling_steps chaguomsingi 12

Idadi ya hatua za kuondoa kelele inayotumika wakati wa uzalishaji wa muundo adimu.

ss_rescale_t chaguomsingi 5

Ukali wa ratiba ya kelele wakati wa uzalishaji wa muundo adimu.

shape_slat_guidance_strength chaguomsingi 7.5

Nguvu ya mwongozo wa classifier-free wakati wa uzalishaji wa umbo.

shape_slat_guidance_rescale chaguomsingi 0.5

Urekebishaji unaotumika kwa mwongozo wakati wa uzalishaji wa umbo; uongeze jiometri inapoonekana kuwa na kelele.

shape_slat_guidance_interval_start chaguomsingi 0.6

Sehemu ya kuondoa kelele ambapo mwongozo wa hatua ya umbo huanza.

shape_slat_guidance_interval_end chaguomsingi 1

Sehemu ya kusitisha mwongozo wa hatua ya umbo, inayowakilishwa kama sehemu ya kuondoa kelele isiyo chini ya shape_slat_guidance_interval_start.

shape_slat_sampling_steps chaguomsingi 12

Idadi ya hatua za kuondoa kelele wakati wa uzalishaji wa umbo.

shape_slat_rescale_t chaguomsingi 3

Ukali wa ratiba ya kelele wakati wa uzalishaji wa umbo.

tex_slat_guidance_strength chaguomsingi 1

Nguvu ya mwongozo wa classifier-free wakati wa uzalishaji wa umbile.

tex_slat_guidance_rescale chaguomsingi 0

Urekebishaji unaotumika kwa mwongozo wakati wa uzalishaji wa umbile; uongeze umbile linapoonekana kuwa na kelele.

tex_slat_guidance_interval_start chaguomsingi 0.6

Sehemu ya kuondoa kelele ambapo mwongozo wa hatua ya umbile huanza.

tex_slat_guidance_interval_end chaguomsingi 0.9

Sehemu ya kusitisha mwongozo wa hatua ya umbile, inayowakilishwa kama sehemu ya kuondoa kelele isiyo chini ya tex_slat_guidance_interval_start.

tex_slat_sampling_steps chaguomsingi 12

Idadi ya hatua za kuondoa kelele wakati wa uzalishaji wa umbile.

tex_slat_rescale_t chaguomsingi 3

Ukali wa ratiba ya kelele wakati wa uzalishaji wa umbile.

decimation_target chaguomsingi 500000

Idadi inayotakiwa ya vertex katika uhamishaji wa GLB.

seed

Seed nasibu inayofanya uzalishaji uweze kurudiwa.

POST /run/trellis-2-lora?wait=20 makadirio → $ 0.25

# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/trellis-2-lora?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.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

const API = "https://api.doitong.ru/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-lora?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.ru/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-lora", 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-lora",
      "input": {
        "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
      },
      "wait_seconds": 20
    }
  }
}

Endesha ombi hili

Ufunguo wa API

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Kumbuka katika kivinjari hiki Pata ufunguo wa API

Kuhusu TRELLIS.2 LoRA Inference

Hutengeneza GLB kutoka kwa `image_url`, kwa kutumia kwa hiari LoRA za safetensors kupitia `sparse_structure_lora_url`, `geometry_lora_url` na `texture_lora_url`. `resolution` ni 512 au 1024 na lazima ilingane na mwonekano wa mafunzo wa adapta. Pia hutoa vidhibiti vya mwongozo na hatua kwa kila hatua, `decimation_target` na `texture_size`.

Vigezo

Tuma jina rasmi au jina asilia, si yote mawili. Majina rasmi

JinaAina ChaguomsingiInaruhusiwa Maelezo

image_urlinahitajika image

Ainaurl · image

URL ya picha chanzo ya kugeuza kuwa modeli ya 3D.

sparse_structure_lora_urlsi lazima

Ainastring | null

Checkpoint ya hiari ya LoRA katika muundo wa safetensors, iliyofunzwa mahsusi kwa denoiser ya muundo adimu.

geometry_lora_urlsi lazima

Ainastring | null

Checkpoint ya hiari ya LoRA katika muundo wa safetensors, iliyofunzwa mahsusi kwa denoiser ya jiometri.

texture_lora_urlsi lazima

Ainastring | null

Checkpoint ya hiari ya LoRA katika muundo wa safetensors, iliyofunzwa mahsusi kwa denoiser ya umbile.

seedsi lazima

Ainainteger | null

Seed nasibu inayofanya uzalishaji uweze kurudiwa.

resolutionsi lazima

Ainaenum

Chaguomsingi512

5121024

Mwonekano wa uzalishaji, ambapo 1024 huchagua pipeline ya cascade. Chagua mwonekano uliotumika kufunza adapta za LoRA ulizotoa; lazima zilingane.

ss_guidance_strengthsi lazima

Ainanumber

Chaguomsingi7.5

0 – 10

Nguvu ya mwongozo wa classifier-free wakati wa uzalishaji wa muundo adimu.

ss_guidance_rescalesi lazima

Ainanumber

Chaguomsingi0.7

0 – 1

Urekebishaji wa mwongozo wakati wa uzalishaji wa muundo adimu. Thamani kubwa hufanya tokeo liwe thabiti zaidi.

ss_guidance_interval_startsi lazima

Ainanumber

Chaguomsingi0.6

0 – 1

Sehemu ya maendeleo ya kuondoa kelele ambapo mwongozo wa muundo adimu huanza.

ss_guidance_interval_endsi lazima

Ainanumber

Chaguomsingi1

0 – 1

Tumia sehemu ya kuondoa kelele iliyo kwenye au juu ya `ss_guidance_interval_start` kubainisha wakati mwongozo wa muundo adimu unasitishwa.

ss_sampling_stepssi lazima

Ainainteger

Chaguomsingi12

1 – 50

Idadi ya hatua za kuondoa kelele inayotumika wakati wa uzalishaji wa muundo adimu.

ss_rescale_tsi lazima

Ainanumber

Chaguomsingi5

1 – 6

Ukali wa ratiba ya kelele wakati wa uzalishaji wa muundo adimu.

shape_slat_guidance_strengthsi lazima

Ainanumber

Chaguomsingi7.5

0 – 10

Nguvu ya mwongozo wa classifier-free wakati wa uzalishaji wa umbo.

shape_slat_guidance_rescalesi lazima

Ainanumber

Chaguomsingi0.5

0 – 1

Urekebishaji unaotumika kwa mwongozo wakati wa uzalishaji wa umbo; uongeze jiometri inapoonekana kuwa na kelele.

shape_slat_guidance_interval_startsi lazima

Ainanumber

Chaguomsingi0.6

0 – 1

Sehemu ya kuondoa kelele ambapo mwongozo wa hatua ya umbo huanza.

shape_slat_guidance_interval_endsi lazima

Ainanumber

Chaguomsingi1

0 – 1

Sehemu ya kusitisha mwongozo wa hatua ya umbo, inayowakilishwa kama sehemu ya kuondoa kelele isiyo chini ya shape_slat_guidance_interval_start.

shape_slat_sampling_stepssi lazima

Ainainteger

Chaguomsingi12

1 – 50

Idadi ya hatua za kuondoa kelele wakati wa uzalishaji wa umbo.

shape_slat_rescale_tsi lazima

Ainanumber

Chaguomsingi3

1 – 6

Ukali wa ratiba ya kelele wakati wa uzalishaji wa umbo.

tex_slat_guidance_strengthsi lazima

Ainanumber

Chaguomsingi1

0 – 10

Nguvu ya mwongozo wa classifier-free wakati wa uzalishaji wa umbile.

tex_slat_guidance_rescalesi lazima

Ainanumber

Chaguomsingi0

0 – 1

Urekebishaji unaotumika kwa mwongozo wakati wa uzalishaji wa umbile; uongeze umbile linapoonekana kuwa na kelele.

tex_slat_guidance_interval_startsi lazima

Ainanumber

Chaguomsingi0.6

0 – 1

Sehemu ya kuondoa kelele ambapo mwongozo wa hatua ya umbile huanza.

tex_slat_guidance_interval_endsi lazima

Ainanumber

Chaguomsingi0.9

0 – 1

Sehemu ya kusitisha mwongozo wa hatua ya umbile, inayowakilishwa kama sehemu ya kuondoa kelele isiyo chini ya tex_slat_guidance_interval_start.

tex_slat_sampling_stepssi lazima

Ainainteger

Chaguomsingi12

1 – 50

Idadi ya hatua za kuondoa kelele wakati wa uzalishaji wa umbile.

tex_slat_rescale_tsi lazima

Ainanumber

Chaguomsingi3

1 – 6

Ukali wa ratiba ya kelele wakati wa uzalishaji wa umbile.

decimation_targetsi lazima

Ainainteger

Chaguomsingi500000

5,000 – 2,000,000

Idadi inayotakiwa ya vertex katika uhamishaji wa GLB.

texture_sizesi lazima

Ainaenum

Chaguomsingi2048

102420484096

Mwonekano wa maumbo yaliyookwa katika uhamishaji wa GLB.

enable_safety_checkersi lazima

Ainaboolean

Chaguomsingitrue

Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.

inahitajika Jina rasmi, pia linakubalika

Vigezo vya faili vinakubali URL ya umma ya https://, data: URI ya hadi 10 MB, au file_url ya upakiaji. Faili

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "trellis-2-lora",
  "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": 250,
    "usd": "0.25",
    "charged": 250,
    "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
    },
    "seed": 42,
    "resolution": 1,
    "sparse_structure_lora_url": "string",
    "geometry_lora_url": "string",
    "texture_lora_url": "string",
    "decimation_target": 1,
    "texture_size": 1
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

Faili zako, chaguo lakoKila outputs[].url ni nakala kwenye hifadhi yetu: huhifadhiwa milele (hutozwa kwa GB kwa mwezi) au 7 siku bila malipo, kulingana na mpangilio wa akaunti yako au ?storage=.

Muundo uleule kwenye kila modelitype, url, content_type, width, height na duration, kwa picha, video na sauti. output ni kitu cha matokeo cha modeli yenyewe.

Sehemu za tokeo

model_glb: object {url, content_type, file_name, file_size}Faili ya GLB iliyo na modeli ya 3D iliyozalishwa.
seed: integerSeed iliyotumika wakati wa uzalishaji.
resolution: integerMwonekano ambao uzalishaji ulifanyika.
sparse_structure_lora_url: string | nullCheckpoint ya LoRA ya muundo adimu iliyotumika wakati wa uzalishaji, ikiwa ilitumika.
geometry_lora_url: string | nullCheckpoint ya LoRA ya jiometri iliyotumika wakati wa uzalishaji, ikiwa ilitumika.
texture_lora_url: string | nullCheckpoint ya LoRA ya umbile iliyotumika wakati wa uzalishaji, ikiwa ilitumika.
decimation_target: integerLengo la idadi ya vertex lililotumika kwenye uhamishaji wa GLB.
texture_size: integerMwonekano wa maumbo yaliyookwa katika uhamishaji wa GLB.

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/trellis-2-lora.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu TRELLIS.2 LoRA Inference

Vigezo

Tokeo

Miundo zaidi: Picha hadi 3D

Trellis Tofauti: 2

Trellis 2 Tofauti: 2

Trellis 2 · Retexture Tofauti: 2

Trellis · Multi Tofauti: 2