Turbo Flux Trainer

Unganisha

Kitambulisho cha modeli turbo-flux-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/turbo-flux-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "images_data_url": "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/turbo-flux-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "images_data_url": "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 = {
    "images_data_url": "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/turbo-flux-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/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": "turbo-flux-trainer",
  "input": {
    "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }
}

Piga modeli ya Turbo Flux Trainer (turbo-flux-trainer) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/turbo-flux-trainer.md

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

{
  "images_data_url": "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/turbo-flux-trainer yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Ombi hili: $ 2.40 salio za API 2,400 · ≈ ₽ 258.19 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

Black Forest Labs Mafunzo Haraka

Hufunza FLUX dev LoRA kwenye zip ya picha, kwa somo au mtindo, ikiwa na vidhibiti vya hatua na kiwango

OpenAPI Markdown

Black Forest Labs · Faili

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.

images_data_url •inahitajika

URL ya kumbukumbu ya picha za mafunzo: toa zip yenye picha zinazoshiriki mtindo, ikiwezekana 10 au zaidi. Seti kubwa za picha huwa bora zaidi.

steps chaguomsingi 1000

Idadi ya hatua za mafunzo ya LoRA.

Ya kina training_style · trigger_phrase · learning_rate · face_crop

training_style chaguomsingi subject

Uteuzi wa mtindo wa mafunzo.

trigger_phrase chaguomsingi ohwx

Toa kishazi cha kichochezi cha kubadilisha `[trigger]` katika maelezo yaliyopo au kutumika kama maelezo yasipotolewa (trigger_work). None huzima neno la kichochezi.

learning_rate chaguomsingi 0.00115

Kasi ya ujifunzaji inayotumika wakati wa mafunzo.

POST /run/turbo-flux-trainer?wait=20 makadirio → $ 2.40

# 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/turbo-flux-trainer?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "images_data_url": "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/turbo-flux-trainer?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "images_data_url": "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 = {
    "images_data_url": "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/turbo-flux-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": "turbo-flux-trainer",
      "input": {
        "images_data_url": "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 Turbo Flux Trainer

Modeli ya mafunzo inayotengeneza uzani maalum wa LoRA kutoka kwenye jalada la zip la picha zilizotolewa kupitia `images_data_url`; inapendekezwa angalau picha 10. Weka `training_style` kuwa subject au mtindo, chagua `trigger_phrase` (chaguo-msingi ohwx), na rekebisha `steps` (1 hadi 10000) na `learning_rate`. `face_crop` inaweza kukata picha kulingana na nyuso zilizotambuliwa. Tokeo ni faili la uzani wa LoRA la diffusers na faili la usanidi.

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo

images_data_urlinahitajika

Ainastring

URL ya kumbukumbu ya picha za mafunzo: toa zip yenye picha zinazoshiriki mtindo, ikiwezekana 10 au zaidi. Seti kubwa za picha huwa bora zaidi.

trigger_phrasesi lazima

Ainastring | null

Chaguomsingiohwx

Toa kishazi cha kichochezi cha kubadilisha `[trigger]` katika maelezo yaliyopo au kutumika kama maelezo yasipotolewa (trigger_work). None huzima neno la kichochezi.

stepssi lazima

Ainainteger

Chaguomsingi1000

1 – 10,000

Idadi ya hatua za mafunzo ya LoRA.

learning_ratesi lazima

Ainanumber

Chaguomsingi0.00115

0 – 0.01

Kasi ya ujifunzaji inayotumika wakati wa mafunzo.

training_stylesi lazima

Ainaenum

Chaguomsingisubject

subjectstyle

Uteuzi wa mtindo wa mafunzo.

face_cropsi lazima

Ainaboolean

Chaguomsingitrue

Washa upunguzaji wa picha kulingana na uso, kwa jaribio la kutafuta uso kwanza.

inahitajika

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t

{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "turbo-flux-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": 2400,
    "usd": "2.40",
    "charged": 2400,
    "refunded": 0
  },
  "input": {
    "images_data_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "output": {
    "diffusers_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
    },
    "config_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"
  }
}

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

diffusers_lora_file: object {url, content_type, file_name, file_size}URL inayoelekeza kwenye uzani wa LoRA uliofunzwa katika muundo wa diffusers.
config_file: object {url, content_type, file_name, file_size}URL ya faili la usanidi la modeli ya diffusers iliyofunzwa.

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

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu Turbo Flux Trainer

Vigezo

Tokeo

Miundo zaidi: Mafunzo

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

Flux 2 Klein 9B Base Trainer Tofauti: 2

FLUX 2 Trainer Tofauti: 2

FLUX 2 Trainer Edit Tofauti: 2