Ruka hadi kwenye maudhui

Ltx 2.3 Quality · Text to Audio · LoRA

Unganisha

Kitambulisho cha modeli ltx-2.3-quality/text-to-audio/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/ltx-2.3-quality/text-to-audio/lora?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ]
  }'

# 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"

Ombi hili: ≈$ 0.70 salio za API 700 · ≈ ₽ 75.31 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Lightricks · Sauti

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.

•inahitajika

Kidokezo kinachoeleza sauti ya kuzalisha.

chaguomsingi 121

Muda wa sauti uliobainishwa kama idadi ya fremu za video za LTX; gawanya `num_frames` kwa `frames_per_second` ili kupata urefu wake wa takribani kwa sekunde.

•inahitajika

Nyongeza za LoRA za LTX-2.3, kila moja ikiwa na kikomo cha 3 GB, na zinazoruhusu hadi maingizo 3. Upakiaji hutokea tu baada ya downloader salama dhidi ya SSRF wa registry kupata kila njia.

Ya kina negative_prompt · frames_per_second · num_inference_steps · guidance_scale · seed · enable_prompt_expansion · enable_safety_checker
chaguomsingi pc game, console game...

Kidokezo hasi kinachobainisha kile ambacho uzalishaji unapaswa kuepuka.

chaguomsingi 24

Kasi ya fremu ya kukokotoa muda wa sauti ya tokeo.

chaguomsingi 15

Jumla ya idadi ya hatua za inference.

chaguomsingi 1

Nguvu ya mwongozo usio na klasifaya.

Seed inayofanya uzalishaji uweze kurudiwa. Kuiweka kuwa None huchagua seed bila mpangilio.

POST /run/ltx-2.3-quality/text-to-audio/lora?wait=20 makadirio → $ 0.70
# 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/ltx-2.3-quality/text-to-audio/lora?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ]
  }'

# 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"

Endesha ombi hili

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

Kuhusu Ltx 2.3 Quality · Text to Audio · LoRA

Hutengeneza sauti kutoka kwa `prompt` ya maandishi na inahitaji orodha ya `loras` yenye hadi LoRA 3 maalum, kila moja ikiwa hadi 3 GB. Muda ni takribani `num_frames` ikigawanywa kwa `frames_per_second`, huku `num_frames` ikiwa kati ya 9 na 481. Pia inakubali `negative_prompt`, `seed`, na `guidance_scale` kati ya 1 na 20.

Vigezo

JinaAina ChaguomsingiInaruhusiwa Maelezo
promptinahitajika
Ainastring
Kidokezo kinachoeleza sauti ya kuzalisha.
num_framessi lazima
Ainainteger
Chaguomsingi121
9 – 481
Muda wa sauti uliobainishwa kama idadi ya fremu za video za LTX; gawanya `num_frames` kwa `frames_per_second` ili kupata urefu wake wa takribani kwa sekunde.
frames_per_secondsi lazima
Ainanumber
Chaguomsingi24
1 – 60
Kasi ya fremu ya kukokotoa muda wa sauti ya tokeo.
num_inference_stepssi lazima
Ainainteger
Chaguomsingi15
8 – 30
Jumla ya idadi ya hatua za inference.
guidance_scalesi lazima
Ainanumber
Chaguomsingi1
1 – 20
Nguvu ya mwongozo usio na klasifaya.
negative_promptsi lazima
Ainastring
Chaguomsingipc game, console game, video game, cartoon, childish, ugly
Kidokezo hasi kinachobainisha kile ambacho uzalishaji unapaswa kuepuka.
seedsi lazima
Ainainteger | null
Seed inayofanya uzalishaji uweze kurudiwa. Kuiweka kuwa None huchagua seed bila mpangilio.
enable_prompt_expansionsi lazima
Ainaboolean
Chaguomsingifalse
Hudhibiti ikiwa upanuzi wa kidokezo umewashwa.
enable_safety_checkersi lazima
Ainaboolean
Chaguomsingitrue
Hudhibiti ikiwa ukaguzi wa usalama umewashwa.
lorasinahitajika
Ainaobject[]
≤ vipengee 3
Nyongeza za LoRA za LTX-2.3, kila moja ikiwa na kikomo cha 3 GB, na zinazoruhusu hadi maingizo 3. Upakiaji hutokea tu baada ya downloader salama dhidi ya SSRF wa registry kupata kila njia.
loras[].pathinahitajika
Ainastring
≤ 2048 characters
URL ya moja kwa moja ya HTTP(S) ya faili ya LoRA .safetensors isiyozidi 3 GB. Upakiaji hutanguliwa na upatikanaji kwa kutumia downloader salama dhidi ya SSRF.
loras[].scalesi lazima
Ainanumber
Chaguomsingi1
0 – 2
Ushawishi wa LoRA kwenye video iliyozalishwa huongezeka kadiri nguvu hii inavyoongezeka ndani ya masafa ya 0.0–2.0.
loras[].transformersi lazima
Ainaenum
Chaguomsingiboth
highlowboth
Bendera ya uteuzi wa Transformer: 'both' inafaa karibu kila mtumiaji wa LTX-2.3 kwa sababu modeli ina transformer moja pekee. Bendera ipo kusaidia usanifu wa baadaye wenye transformer nyingi.
inahitajika

Tokeo

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ltx-2.3-quality/text-to-audio/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": 700,
    "usd": "0.70",
    "charged": 700,
    "refunded": 0
  },
  "input": {
    "loras": [
      {
        "path": "https://example.com/your-file.safetensors"
      }
    ],
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "audio": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_name": "0-output.mp3",
      "file_size": 1843200
    },
    "seed": 42,
    "prompt": "string"
  },
  "outputs": [
    {
      "type": "audio",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp3",
      "content_type": "audio/mpeg",
      "file_size": 1843200,
      "duration": 12,
      "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
audio
object {url, content_type, file_name, file_size}Sauti iliyotolewa na modeli.
seed
integerSeed halisi iliyotumika wakati wa uzalishaji.
prompt
stringKidokezo cha uzalishaji, pamoja na upanuzi wowote uliotumika kabla ya matumizi.

Miundo zaidi: Sauti

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/ltx-2.3-quality/text-to-audio/lora.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt