Ruka hadi kwenye maudhui

Bytedance Omnihuman V1.5

Unganisha

Kitambulisho cha modeli bytedance/omnihuman/v1.5
# 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/v1.5?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: $ 1.60 salio za API 1,600 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
ByteDance Usawazishaji wa Midomo na Avatari Usawazishaji wa midomohadi 1080p #image-to-video#lipsync

OmniHuman 1.5 huongeza kidokezo cha maandishi, maski ya mzungumzaji, hali ya turbo na chaguo la 720p au 1080p

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.

Kidokezo cha maandishi kinachoelekeza uzalishaji wa video.

•inahitajika image_url
Dondosha faili, au

URL ya picha inayotoa chanzo cha uzalishaji wa video.

•inahitajika audio_url
Dondosha faili, au

URL ya chanzo cha sauti kwa uzalishaji wa video, yenye kikomo cha muda kulingana na mwonekano: chini ya sekunde 60 kwa 720p, au chini ya sekunde 30 kwa 1080p.

resolution chaguomsingi 1080p

Mwonekano wa video ya tokeo: 720p hutoa uzalishaji wa haraka na ubora wa juu wenye sauti hadi sekunde 60, huku 1080p ikiruhusu sauti hadi sekunde 30. Chaguo chaguomsingi ni 1080p.

Ya kina mask · turbo_mode
mask_url
Dondosha faili, au

URL ya maski inayomtambulisha mtu anayezungumza kupitia eneo lake jeupe; baada ya maski kutumika kwenye picha, ni mtu huyo pekee anayezungumza.

POST /run/bytedance/omnihuman/v1.5?wait=20 makadirio → $ 1.60
# 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/v1.5?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 V1.5

Huamsha picha ya mtu kutoka faili ya sauti. `prompt` ya hiari huongoza tukio, na `mask_url` huzuia kuzungumza kwenye eneo jeupe la maski. `turbo_mode` hubadilisha kiasi kidogo cha ubora kwa kasi. `resolution` ni 720p au 1080p; sauti inaweza kuwa hadi sekunde 60 kwa 720p na sekunde 30 kwa 1080p.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo
promptsi lazima
Ainastring | null
Kidokezo cha maandishi kinachoelekeza uzalishaji wa video.
image_urlinahitajika image
Ainaurl · image
URL ya picha inayotoa chanzo cha uzalishaji wa video.
mask_urlsi lazima mask
Ainaurl · image
URL ya maski inayomtambulisha mtu anayezungumza kupitia eneo lake jeupe; baada ya maski kutumika kwenye picha, ni mtu huyo pekee anayezungumza.
audio_urlinahitajika audio
Ainaurl · audio
URL ya chanzo cha sauti kwa uzalishaji wa video, yenye kikomo cha muda kulingana na mwonekano: chini ya sekunde 60 kwa 720p, au chini ya sekunde 30 kwa 1080p.
turbo_modesi lazima
Ainaboolean
Chaguomsingifalse
Washa hii ili kupunguza kiasi kidogo cha ubora wa video kwa ajili ya uzalishaji wa haraka.
resolutionsi lazima
Ainaenum
Chaguomsingi1080p
720p1080p
Mwonekano wa video ya tokeo: 720p hutoa uzalishaji wa haraka na ubora wa juu wenye sauti hadi sekunde 60, huku 1080p ikiruhusu sauti hadi sekunde 30. Chaguo chaguomsingi ni 1080p.
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/v1.5",
  "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": 1600,
    "usd": "1.60",
    "charged": 1600,
    "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/v1.5.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt