Ruka hadi kwenye maudhui

Bytedance Omnihuman V2

Unganisha

Kitambulisho cha modeli bytedance/omnihuman/v2
# 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/bytedance/omnihuman/v2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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"

Faili kama mfano: $ 1.05 salio za API 1,050 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
ByteDance Usawazishaji wa Midomo na Avatari Usawazishaji wa midomo #image-to-video#lipsync

OmniHuman 2 hushughulikia sauti ndefu ya sekunde 4 hadi 300, ikiwa na kidokezo cha hiari cha mandhari ya lugha nyingi

ByteDance · Video

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.

Udhibiti sahihi wa mandhari, miondoko na kamera kupitia kidokezo cha hiari cha maandishi kilichoandikwa katika lugha yoyote inayotumika: Indonesian, Spanish (Mexican), Korean, Japanese, English, au Chinese.

•inahitajika image_url
Dondosha faili, au

URL inayoelekeza kwenye picha ambayo video inazalishwa kutoka kwayo. Picha lazima iwe na vipimo vyote kati ya pikseli 300–6000 na uwiano wa upana/urefu kati ya 0.4–2.5. Faili zina kikomo cha 30 MB na lazima zitumie umbizo la jpeg, png, webp, bmp, tiff, gif, heic au heif.

•inahitajika audio_url
Dondosha faili, au

Toa sauti chanzo ya video kupitia URL inayoelekeza kwenye faili yenye urefu wa sekunde 4–300. Faili lazima iwe wav au mp3 na isiwe kubwa kuliko 15 MB.

POST /run/bytedance/omnihuman/v2?wait=20 makadirio → $ 1.05
# 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/bytedance/omnihuman/v2?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  }'

# 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"

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 Bytedance Omnihuman V2

Hugeuza picha ya mtu na faili ya sauti kuwa video ya mtu anayezungumza. Sauti lazima iwe wav au mp3, hadi 15 MB, kati ya sekunde 4 na 300. Picha inaweza kuwa hadi 30 MB, ikiwa na pande za pikseli 300 hadi 6000. `prompt` ya hiari huongoza tukio, mwendo na kamera katika lugha kadhaa zinazotumika.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo
promptsi lazima
Ainastring | null
Udhibiti sahihi wa mandhari, miondoko na kamera kupitia kidokezo cha hiari cha maandishi kilichoandikwa katika lugha yoyote inayotumika: Indonesian, Spanish (Mexican), Korean, Japanese, English, au Chinese.
image_urlinahitajika image
Ainaurl · image
URL inayoelekeza kwenye picha ambayo video inazalishwa kutoka kwayo. Picha lazima iwe na vipimo vyote kati ya pikseli 300–6000 na uwiano wa upana/urefu kati ya 0.4–2.5. Faili zina kikomo cha 30 MB na lazima zitumie umbizo la jpeg, png, webp, bmp, tiff, gif, heic au heif.
audio_urlinahitajika audio
Ainaurl · audio
Toa sauti chanzo ya video kupitia URL inayoelekeza kwenye faili yenye urefu wa sekunde 4–300. Faili lazima iwe wav au mp3 na isiwe kubwa kuliko 15 MB.
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": "bytedance/omnihuman/v2",
  "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": 1050,
    "usd": "1.05",
    "charged": 1050,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/avatar/talking_avatar.jpg",
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3"
  },
  "output": {
    "video": {
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_name": "0-output.mp4",
      "file_size": 1843200
    },
    "duration": 5
  },
  "outputs": [
    {
      "type": "video",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.mp4",
      "content_type": "video/mp4",
      "file_size": 1843200,
      "width": 1280,
      "height": 720,
      "duration": 5,
      "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"
  }
}
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
video
object {url, content_type, file_name, file_size}Faili ya video inayotokana.
duration
number

Miundo zaidi: Usawazishaji wa Midomo na Avatari

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/bytedance/omnihuman/v2.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt