TRELLIS.2 Trainer

ᠵᡠᠸᡝᠪᡠᠮᠪᡳ

ᠮᠣᡩᡝᠯ id trellis-2-lora-trainer

# 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-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "data_url": "https://example.com/your-file.zip"
  }'

# 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-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "data_url": "https://example.com/your-file.zip"
  }),
});
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 = {
    "data_url": "https://example.com/your-file.zip",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/trellis-2-lora-trainer", 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/mnc/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-trainer",
  "input": {
    "data_url": "https://example.com/your-file.zip"
  }
}

TRELLIS.2 Trainer ᠮᠣᠳᡝᠯ (trellis-2-lora-trainer) ᠪᡝ Doitong API ᠵᠠᠯᡳᠨᡩᡝ ᠠᠰᡠᠮᠪᡳ. ᠠᡤᡝᠨᡨᡳ ᡩᠠᡳᠯᠠᠨ: https://doitong.com/mnc/developers/models/trellis-2-lora-trainer.md

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

{
  "data_url": "https://example.com/your-file.zip"
}

ᡝᡵᡝᠮᡝ ᠪᡠᠮᡝᠨᡳ ᠠᠨᠠᠮᡝ "queued" ᡳᠨᡠ "running" ᠪᡝ, GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 ᠪᡝ ᠠᠨᠠᠮᡝ "succeeded" ᠪᡝᠴᡳ ᠠᠰᡠᠮᠪᡳ; ᡶᡳᠯᡝ ᠪᡝ outputs[].url ᠪᡝᠴᡳ ᠣᠨᡩᠣᠮᡝ. POST https://api.doitong.ru/v1/quote/trellis-2-lora-trainer ᠪᡝ ᡝᠮᡠ ᠪᡠᠶᡝᠮᡝ ᠪᡝ ᠠᠰᡠᠮᠪᡳᡩᡝ ᠵᠠᠯᡤᠠᠨ ᠪᡝ ᠶᠠᠪᡠᠮᠪᡳ ᠰᡳᠨᡳ ᠠᠮᡤᠠ ᠠᠰᡠᠮᠪᡳ ᠣᠯᡥᠣᠮᡝ.

ᠵᠠᠨᡳ ᡥᠠᠯᠠᠮᠠ ᡥᡡᠯᠠᠨᡳ ᡶᡳᠯᡝ: $15.973 15,973 API ᠺᠷᡝᡩᡳᠲ · ≈ ₽1,684.56 ᠰᡳᠨᡳ ᡶᡳᠯᡝ ᠵᠠᠯᡤᠠᠨ ᠠᠰᡠᠮᠪᡳᠨᡳ ᠠᠯᡳᠮᠪᡳ ᡝᡵᡝ ᠵᠠᠯᡳᠨᡩᡝ ᠠᠰᡠᠮᠪᡳ

API ᡩᠠᠮᡠᠨ ᡤᠠᠯᠠ

Microsoft ᠰᠠᠮᠠᠨ

ᡝᠮᡠ ᡤᡳᠯᡤᠠᠨ 3D ᠠᠰᡳᠨᡳ zip ᠠᠴᠠ Trellis 2 ᡩᡝ LoRA ᠠᠯᡳᠨ ᡠᠯᠠᡥᠠᠮᡝ᠂ ᡠᠮᡝ ᡳᠯᠠᠨ ᡩᡝᠯᡤᡳᠨᡳ ᠵᠠᠰᡳᠮᡝᠨ ᡩᡝ

OpenAPI Markdown

Microsoft · ᡶᡳᠯᡝ

ᡳᠨᡝ ᡝᠮᡠᠨᡳᠩᡤᡝ ᡝᡵᡝᠮᡝ ᡩᡝ

ᡝᡵᡝ ᠵᡠᠯᡝᠨ ᡩᡝ ᡤᡝᡪᡳᠯᡝᠨ ᠪᠠᠶᠠᠨᠠᠮᡝ ᠠᠮᡪᠠᠯᠠ ᡶᡳᠯᡝᠮᡝ ᠪᡝᠶᡝᠮᡝ᠃ API ᠵᡳᡵᡤᠠᡳ ᡤᠠᡳᡥᠠᡩᡝ ᡤᡝᡪᡳᠯᡝᠨ ᠵᠠᠯᠠᠨᠠᠮᡝ ᠪᡠᠶᡝᠮᡝ ᠮᡠᠰᡝᡳ ᠰᡠᠯᡠᠨᡩᡝ ᠪᠠᠶᠠᠨᠠᠮᡝ᠂ ᠝ᠮᡤᡳ ᠮᡠᠰᡝ ᠠᠶᠠᠨ 7 ᡥᠠᠨ ᠰᠠᡳᠨᠠᠮᡝ᠃

ᡤᡳᠰᡠᠨ ᠪᡠᠶᡝᠮᡝ

ᡝᠮᡠ ᠵᡠᠯᡤᡝᠨ ᡩᡝ ᡤᡝᠯᡳ

ᠰᡳᠨᡳ ᡩᠣᠰᡳᠮᡝ ᠵᡝᠨᡝᠰᡠᠨ ᡳ ᡠᠯᡤᡝᠰᡳ ᡩᡝ ᡝᠪᡠᠮᠪᡳ

$15.973ᡝᠮᡠ ᠵᡠᠯᡤᡝ ᡩᡝ

15,973 API ᠺᠷᡝᡩᡳᠲ · ≈ ₽1,684.56

ᠵᠠᠯᡤᠠᠨ: $1.751 ᠰᡳ

1 ᡩᡠᠯᡝᠮᡝ × $15.9723 ᠵᠠᠯᠠᠨᠠᠮᡝ · $15.973

ᠮᠠᠩᡤᡳ ᠰᡠᠯᡠᠮᡝ ᡠᠯᠠᠮᡝ ᡝᠨᡝᠩᡤᡳ ᠠᠪᠠᠮᡝ᠈ ᡝᠷᡳᠨ ᠠᡴᡡ ᡤᡳᠰᡠᠨ ᡩᡝ ᠠᠮᡝᠪᡠᠮᡝ ᠠᡵᠠᠮᡝ

resolution ᠵᡠᠯᡝ 512

rank ᠵᡠᠯᡝ 32

training_steps ᠵᡠᠯᡝ 1000

ᠰᡳᠨᡳ ᡶᡳᠯᡝ ᡠᠯᡤᡝᠰᡳ ᡩᡝᠯᡝ ᠵᡝᠨᡝᠰᡠᠨ (ᡠᠯᡩᡠᠰᡳᠨ᠂ ᠰᡳᠯᡤᠠᠨ᠂ ᡶᡠᠯᡤᡳᠶᠠᠨ ᡠᠨᡩᡝᠩᡤᡳ) ᡩᡠᠯᡝᠮᠪᡳ; ᡤᡝᠯᡳ ᠵᡠᠯᡤᡝᠨ ᠵᡝᠨᡝᠰᡠᠨ ᡤᡝᠯᡳ ᡥᡝᠰᡝ ᠪᡳᠮᠪᡳ ᡠᠨᡩᡝᠩᡤᡳ᠈ ᡝᠮᡠ ᠵᡠᠯᡤᡝᠨ ᡩᡝ ᡝᠮᡠ ᠵᡝᠨᡝᠰᡠᠨ ᠵᡠᠸᡝᠮᡝ ᠰᡳᠨᡳ ᠵᡠᠯᡤᡝᠨ ᡩᡝ ᡝᠮᡠ ᠵᡝᠨᡝᠰᡠᠨ ᠵᠠᠯᡠᠪᡠᠮᠪᡳ᠉

ᠵᠠᠯᡤᠠᠨ ᠵᠠᠯᡳᠨ ᠳᠡ: POST /quote/{id}

ᡤᡳᠰᡠᠨ ᠪᡠᠶᡝᠮᡝ

ᠵᠠᡴᡠᠨᡳ ᠵᡠᠯᡝ ᡩᡝᡵᡤᡳ ᡩᡝᠪᡝᠰᡠᠮᡝ ᠵᡠᠯᡤᡝ ᠪᡠᠶᡝᠮᡝ᠈ ᡳᠨᡳ ᡤᡳᠰᡠᠨ ᠪᠠᡳ ᡝᠨᡝᠩᡤᡳ ᠠᠮᠪᡳ

resolution ᠵᡠᠯᡝ 512

ᠵᡝᠰᡝᠨ ᡳ ᠵᠠᠯᠠᠨ ᠪᡝ ᡩᠠᠯᠠᠮᡝ ᡳ ᠵᠠᠯᠠᠨ ᡩᡝ ᡝᠮᡠ ᠪᡳᠮᡝ ᡳᠨᡠ᠉

rank ᠵᡠᠯᡝ 32

LoRA ᡳ ᠵᠠᠯᠠᠨ ᡳ rank᠉ ᠠᠮᠪᠠ ᠪᡳᠮᡝ capacity ᠵᡝᠯᡥᡝᠮᠪᡳ᠉

data_url •ᡴᠠᠷᠠᡴᡡ

ᡩᠠᠯᠠᠮᡝ ᡳ ᠪᠠᠷᠠᠨ ᡳ URL᠉ raw 3D ᡝᠮᡤᡳ ᠪᡝ .zip ᡩᡝ ᠪᠠᠨᡩᡠᡥᠠᠨ ᡩᠠᠯᠠᠮᡝᠨᡝᠮᠪᡳ᠂ ᡝᠮᡝᠯᡝ TRELLIS.2 ᡩᠠᠯᠠᠮᡝ ᡳ zip ᠪᡝ data_preprocessing ᡩᡝ ᠪᡠᠶᡝᠮᡝᠨᡝᠮᠪᡳ᠉

training_steps ᠵᡠᠯᡝ 1000

ᠵᡝᠰᡝᠨ ᡳ ᡤᡝᠮᡠ ᠵᡝᠯᡥᡝᠨ᠉

denoisers

sparse_structure᠂ geometry᠂ texture ᡩᡝᡵᡳ 1–3 ᡝᠮᡠᠨ ᡩᠠᠯᠠᠮᡝᠨᡝᠮᠪᡳ ᡳ TRELLIS.2 ᠵᡝᠰᡝᠨ ᡳ ᠰᡝᠯᡝᠮᠪᡳ᠉

ᠵᡠᠯᡤᡝ ᠵᡝᡵᡤᡳ learning_rate

learning_rate ᠵᡠᠯᡝ 0.0001

LoRA ᡳ ᠵᠠᠯᠠᠮᠪᡝ ᡳ learning rate᠉

POST /run/trellis-2-lora-trainer?wait=20 ᠵᠠᠯᡳᠨ → $15.973

# 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-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "data_url": "https://example.com/your-file.zip"
  }'

# 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-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "data_url": "https://example.com/your-file.zip"
  }),
});
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 = {
    "data_url": "https://example.com/your-file.zip",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/trellis-2-lora-trainer", 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-trainer",
      "input": {
        "data_url": "https://example.com/your-file.zip"
      },
      "wait_seconds": 20
    }
  }
}

ᡝᠨᡳ ᠵᠠᠯᡳᠨ ᠪᡝ ᠵᠠᠯᠠᠨᠠᠮᡝ

API ᠵᠠᠯᠠᠨ

ᡳᠨᡝ ᠵᠠᠯᠠᠨ ᡝᡵᡝ ᠪᡠᡵᡝᠪᡝᡵᡳ ᡩᡝ ᠪᡳᠮᡝ᠈ Doitong API ᡩᡝ ᠵᡝᠯᡤᡳ ᡩᠠᡵᠠᠮᡝ᠈ Remember ᠵᡠᠯᡝᠮᡝ ᡤᡳᠯᠠᠮᡝ localStorage ᡩᡝ ᠰᡠᠯᡝᠮᡝ ᠪᡳᠮᡝ ᡝᡵᡤᡝᠨ ᡩᡝ ᡳᠨᡠ ᠠᡶᡠᠯᠠᠮᠪᡳ API ᠵᠠᠯᠠᠨ ᠠᠪᠠᠮᡝ

TRELLIS.2 Trainer ᡠᡵᡝᠮᡝ

`data_url` ᡩᡝ ᡤᠠᠯᠠᠮᡝ ᠪᠠᠶᡳᡥᠠ zip ᠠᠴᠠ ᠠᠯᡳᠨ ᡩᠠᠯᡳᠨ ᡠᠯᠠᡥᠠᠮᡝ᠂ ᡤᡳᠯᡤᠠᠨ 3D ᠠᠰᡳᠨ ᠶᠠᠪᡠᠨ ᠵᠠᠰᡳᠮᡝᠨ ᡩᠠᠯᡳᠨ ᠪᠠᠶᡳᠮᠪᡳ᠉ `denoisers` 1 ᠠᠴᠠ 3 ᠮᡠᠶᠠᠯᠠᠨ ᠰᠣᠩᡤᠣᠯᠣᠮᡝ᠂ ᡝᠮᡠ ᡩᡝ ᡝᠮᡠ ᠠᠯᡳᠨ ᠪᠠᠶᡳᠮᠪᡳ᠉ ᠵᠠᠰᡳᠮᡝᠨ᠄ `resolution` 512 ᠶᠠᠪᡠᠨ 1024᠂ `rank` 16᠂ 32 ᠶᠠᠪᡠᠨ 64᠂ `learning_rate`᠂ ᠶᠠᠪᡠᠨ `training_steps` 100 ᠠᠴᠠ 10000 ᡩᡝ᠉ ᠠᠯᡳᠨ᠂ ᠪᠠᠶᠠᠨ ᠠᡴᡡ ᠶᠠᠪᡠᠨ ᠳᠠᠬᡳ ᠠᠰᡳᠯᠠᠮᡝ ᠪᠠᠶᡳᠮᠪᡳ᠉

ᠵᠠᡴᡠᠨ

ᠵᡝᡵᡤᡳᡠᠯᠠᠮᡝ ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝᠠᠪᠠᠮᡝ ᠵᠠᠪᡠᠨ ᠵᠠᠯᠠᠨᡳ ᡤᡳᠰᡠᠨ

data_urlᡴᠠᠷᠠᡴᡡ

ᡠᠯᠠᠮᡝstring

denoisersᠵᡠᠯᡝ

ᡠᠯᠠᠮᡝenum[]

≤ 3 ᡴᡝᠮᡠᠨ

sparse_structure᠂ geometry᠂ texture ᡩᡝᡵᡳ 1–3 ᡝᠮᡠᠨ ᡩᠠᠯᠠᠮᡝᠨᡝᠮᠪᡳ ᡳ TRELLIS.2 ᠵᡝᠰᡝᠨ ᡳ ᠰᡝᠯᡝᠮᠪᡳ᠉

resolutionᠵᡠᠯᡝ

ᡠᠯᠠᠮᡝenum

ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ512

5121024

ᠵᡝᠰᡝᠨ ᡳ ᠵᠠᠯᠠᠨ ᠪᡝ ᡩᠠᠯᠠᠮᡝ ᡳ ᠵᠠᠯᠠᠨ ᡩᡝ ᡝᠮᡠ ᠪᡳᠮᡝ ᡳᠨᡠ᠉

rankᠵᡠᠯᡝ

ᡠᠯᠠᠮᡝenum

ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ32

163264

LoRA ᡳ ᠵᠠᠯᠠᠨ ᡳ rank᠉ ᠠᠮᠪᠠ ᠪᡳᠮᡝ capacity ᠵᡝᠯᡥᡝᠮᠪᡳ᠉

learning_rateᠵᡠᠯᡝ

ᡠᠯᠠᠮᡝnumber

ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ0.0001

0.000001 – 0.01

LoRA ᡳ ᠵᠠᠯᠠᠮᠪᡝ ᡳ learning rate᠉

training_stepsᠵᡠᠯᡝ

ᡠᠯᠠᠮᡝinteger

ᠵᠠᠯᠠᠨᡳ ᠵᡠᠯᡝ1000

100 – 10,000

ᠵᡝᠰᡝᠨ ᡳ ᡤᡝᠮᡠ ᠵᡝᠯᡥᡝᠨ᠉

ᡴᠠᠷᠠᡴᡡ

ᠪᡠᠶᡝᠮᡝ

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "trellis-2-lora-trainer",
  "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": 15973,
    "usd": "15.973",
    "charged": 15973,
    "refunded": 0
  },
  "input": {
    "data_url": "https://example.com/your-file.zip"
  },
  "output": {
    "adapters": [
      {
        "denoiser": "sparse_structure",
        "resolution": 1,
        "lora_file": {
          "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
        },
        "rank": 1,
        "training_steps": 1,
        "learning_rate": 1.0
      }
    ],
    "failed": [
      {
        "denoiser": "sparse_structure",
        "error": "string"
      }
    ],
    "preprocessed_data_file": {
      "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}

ᡤᡝᠯᡝᠮᡝ ᡥᡡᠯᡤᡠᠨᡳ ᡳᠨᡠᡝᠯᡝᡥᡝ outputs[].url ᠰᡠᠯᡠᠨ ᡩᡝ ᠰᡳᡵᡝ ᡶᡳᠯᡝ᠈ ᠝ᠮᡤᡳ ᠮᡠᠰᡝ ᠠᠪᠠᠯᡳ ᠵᡝᠮᡤᡳᠨ GB-ᠪᡳᠶᠠ ᠵᡝᠮᡤᡳᠨ ᠪᡝ ᡝᠮᡠᠯᡝᠮᡝ ᠠᠪᠠᠯᡳ 7 ᡥᠠᠨ ᠰᡳᠯᡤᠠᠨ ᡩᡝ᠈ ᠰᡳᠨᡳ ᠪᠠᠯᠠᠨᠰᡳ ᠵᡠᠶᡝᡵᡝᠨ ᠠᠪᠠᠯᡳ ?storage= ᡩᡝ ᡝᠵᡝᠨ ᡥᠠᠯᠠᠮᡝ᠉

ᡝᠮᡠ ᡤᡳᠰᡠᠨ ᡝᠮᡠ ᠮᠣᡩᡝᠯ ᡩᡝtype, url, content_type, width, height ᠮᠠᠩᡤᡳ duration᠈ ᠵᠠᠯᠠᠨ᠈ ᠪᡠᠵᡠᠮᠪᡳ ᠮᠠᠩᡤᡳ ᠵᡝᡵᡤᡳ ᡩᡝᠨᡳ᠈ output ᠮᠣᡩᡝᠯᡳᠨᡳ ᡝᠮᡠ ᠵᠠᠯᠠᠨ

ᠪᡠᠶᡝᠮᡝᠨᡳ ᡤᡳᠰᡠᠨ

adapters: array of object {denoiser, resolution, lora_file, rank, training_steps, learning_rate}LoRA ᡳ ᡶᡳᠯᡝᠰᡝ ᡳ trellis-2-lora ᡳ ᠵᠠᠯᠠᠮᠪᡳ ᡳ ᡶᡳᠯᡩ ᡩᡝ ᡩᠠᠯᠠᠮᠪᡳ᠉
failed: array of object {denoiser, error}ᠠᠮᡤᠠᠯᠠᠮᡝ ᡳᠯᡥᡝᠨᡝᠮᠪᡳ ᡳ denoiser ᡳ ᠵᡝᠰᡝᠨ ᡳ ᡩᡠᠯᡝᠨ᠉
preprocessed_data_file: object {url, content_type, file_name, file_size}ᡝᡵᡝᠮᡝ ᠵᡝᠰᡝᠨᡳ TRELLIS.2 ᡳ zip ᠪᡝ ᠵᡝᠰᡝᠨ ᡩᡝ ᡠᠯᠠᠮᡝᠨᡝᠮᠪᡳ᠉

AI ᠠᡤᡝᠨᡨᡳ ᡠᠴᡠᠷᡳ᠈ ᡝᡵᡝ ᡩᡝᠪᡝᡵᡳ Markdown ᠰᡳᠨᡩᠠᡵᡳ https://doitong.com/mnc/developers/models/trellis-2-lora-trainer.md. ᡝᡵᡝ ᠮᠣᡩᡝᠯ ᠵᠠᡴᡠᠨ ᠰᡠᠯᡠᠮᡝ https://doitong.com/developers/llms.txt

ᡳᠨᡝ ᡝᠮᡠᠨᡳᠩᡤᡝ ᡝᡵᡝᠮᡝ ᡩᡝ

ᡤᡳᠰᡠᠨ ᠪᡠᠶᡝᠮᡝ

ᡝᠨᡳ ᠵᠠᠯᡳᠨ ᠪᡝ ᠵᠠᠯᠠᠨᠠᠮᡝ

TRELLIS.2 Trainer ᡠᡵᡝᠮᡝ

ᠵᠠᡴᡠᠨ

ᠪᡠᠶᡝᠮᡝ

ᡝᠯᡤᡳ ᡩᠠᠯᡳᠨ: ᠰᠠᠮᠠᠨ

ERNIE-Image Trainer

FLUX 2 [klein] 9b Base Trainer ᡠᠯᡤᡳᠨ: 2

Flux 2 Klein 9B Base Trainer ᡠᠯᡤᡳᠨ: 2

FLUX 2 Trainer ᡠᠯᡤᡳᠨ: 2