Ruka hadi kwenye maudhui

Sa2VA 4B Video

Unganisha

Kitambulisho cha modeli sa2va/4b/video
# 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/sa2va/4b/video?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",
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# 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"

Faili kama mfano: $ 0.40 salio za API 400 · ≈ ₽ 41.88 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
ByteDance Maono #multimodal#vision

Modeli ndogo ya Sa2VA inayojibu maswali kuhusu video na kurudisha video za barakoa

ByteDance · Maandishi

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 kilichotolewa kwa ukamilishaji wa gumzo.

•inahitajika video_url
Dondosha faili, au

URL inayoelekeza kwenye video ya ingizo.

Ya kina num_frames_to_sample

Idadi ya fremu za video za kuchukua sampuli, kutoka 5 hadi 100. Hutumia 32 ikiwa haijatolewa.

POST /run/sa2va/4b/video?wait=20 makadirio → $ 0.40
# 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/sa2va/4b/video?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",
    "video": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  }'

# 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 Sa2VA 4B Video

Huchukua `video_url` na `prompt` ya maandishi, na kurudisha jibu la maandishi pamoja na video za barakoa zilizo na lebo. `num_frames_to_sample` huweka idadi ya fremu zinazochanganuliwa, kutoka 5 to 100, na chaguo-msingi ni 32 ikiwa haijatolewa. Huu ni ukubwa wa 4B kwa ingizo la video.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo
promptinahitajika
Ainastring
Kidokezo kilichotolewa kwa ukamilishaji wa gumzo.
video_urlinahitajika video
Ainaurl · video
URL inayoelekeza kwenye video ya ingizo.
num_frames_to_samplesi lazima
Ainainteger | null
5 – 100
Idadi ya fremu za video za kuchukua sampuli, kutoka 5 hadi 100. Hutumia 32 ikiwa haijatolewa.
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": "sa2va/4b/video",
  "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": 400,
    "usd": "0.40",
    "charged": 400,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "output": {
    "output": "<p>  Two children  </p>   [SEG]  are jumping on  <p>  a bed  </p>   [SEG]  .<|im_end|>",
    "masks": [
      {
        "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
output
stringTokeo lililotengenezwa na modeli.
masks
array of object {url, content_type, file_name, file_size}Kamusi inayopangisha lebo kwenye video za barakoa.

Miundo zaidi: Maono

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/sa2va/4b/video.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt