Ruka hadi kwenye maudhui

Sam 3 · Video RLE

Unganisha

Kitambulisho cha modeli sam-3/video-rle
# 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/sam-3/video-rle?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Faili kama mfano: $ 0.095 salio za API 95 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API
Meta Video hadi Video #segmentation#mask#real-time#rle

Ugawaji wa video wenye uanzishaji kupitia URL ya kinyago, udhibiti wa faharasa ya fremu na kiwango cha chini cha utambuzi kilichopunguzwa

Meta · 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.

chaguomsingi

Kidokezo cha segmentation kinachotumia vitu vingi vinavyofuatiliwa kupitia maelezo yaliyotenganishwa kwa koma, kama vile 'person, cloth'.

•inahitajika video_url
Dondosha faili, au

URL ya video kwa ajili ya segmentation.

Ya kina mask · detection_threshold · frame_index · apply_mask · boundingbox_zip · point_prompts · box_prompts
mask_url
Dondosha faili, au

URL ya maski kwa matumizi ya awali.

chaguomsingi 0.5

Kikomo cha kujiamini cha utambuzi, chaguomsingi ikiwa 0.5 kwa vitu vilivyopo na 0.7 kwa vipya. Ndani ya masafa ya 0.0–1.0, thamani ndogo hupunguza usahihi kwa kuongeza idadi ya utambuzi; jaribu 0.2–0.3 vidokezo vya maandishi vinaposhindwa.

chaguomsingi 0

Faharasa ya fremu kwa mwingiliano wa awali wakati wa kutoa mask_url.

chaguomsingi []

Orodha ya vidokezo vya nukta inayobainisha faharasa za fremu.

chaguomsingi []

Orodha ya vidokezo vya visanduku, ikiwa na frame_index ya hiari kwa kila ingizo.

POST /run/sam-3/video-rle?wait=20 makadirio → $ 0.095
# 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/sam-3/video-rle?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "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.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 Sam 3 · Video RLE

Hugawa video kwa SAM 3 kwa kutumia `prompt` ya maandishi, maelekezo ya nukta au kisanduku, au kinyago cha awali kutoka `mask_url` kinachotumika kwenye `frame_index`. `detection_threshold` huanzia 0.01 hadi 1, na thamani za chini kama 0.2 hadi 0.3 zinaweza kusaidia maelekezo ya maandishi yanaposhindwa. Inaweza kurejesha zip ya visanduku vya mipaka kwa kila fremu kupitia `boundingbox_zip`.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo
video_urlinahitajika video
Ainaurl · video
URL ya video kwa ajili ya segmentation.
mask_urlsi lazima mask
Ainaurl · image
URL ya maski kwa matumizi ya awali.
promptsi lazima
Ainastring
Chaguomsingi
Kidokezo cha segmentation kinachotumia vitu vingi vinavyofuatiliwa kupitia maelezo yaliyotenganishwa kwa koma, kama vile 'person, cloth'.
point_promptssi lazima
Ainaobject[]
Chaguomsingi[]
Orodha ya vidokezo vya nukta inayobainisha faharasa za fremu.
point_prompts[].xsi lazima
Ainainteger | null
Nafasi ya kidokezo kwenye mhimili wa X.
point_prompts[].ysi lazima
Ainainteger | null
Nafasi ya kidokezo kwenye mhimili wa Y.
point_prompts[].labelsi lazima
Ainaenum
01
Lebo ya mandhari ya mbele/mandharinyuma: 1 huonyesha mandhari ya mbele; 0 huonyesha mandharinyuma.
point_prompts[].object_idsi lazima
Ainainteger | null
Kitambulisho cha hiari kinachopanga vidokezo vinavyoboresha kitu kimoja. Ikiwa maandishi pia yametolewa kama kidokezo, kitambulisho hiki huamua ni kitu gani kilichogunduliwa ambacho pointi hizo huboresha.
point_prompts[].frame_indexsi lazima
Ainainteger | null
Faharasa inayotambulisha fremu ya mwingiliano.
box_promptssi lazima
Ainaobject[]
Chaguomsingi[]
Orodha ya vidokezo vya visanduku, ikiwa na frame_index ya hiari kwa kila ingizo.
box_prompts[].x_minsi lazima
Ainainteger | null
Koordinati ya chini ya x ya kisanduku.
box_prompts[].y_minsi lazima
Ainainteger | null
Koordinati ya chini ya y ya kisanduku.
box_prompts[].x_maxsi lazima
Ainainteger | null
Kiwianishi cha juu zaidi cha X cha kisanduku.
box_prompts[].y_maxsi lazima
Ainainteger | null
Kiwianishi cha juu zaidi cha Y cha kisanduku.
box_prompts[].object_idsi lazima
Ainainteger | null
Kitambulisho cha hiari kinachopanga visanduku vinavyoboresha kitu kimoja.
box_prompts[].frame_indexsi lazima
Ainainteger | null
Faharasa inayotambulisha fremu ya mwingiliano.
apply_masksi lazima
Ainaboolean
Chaguomsingifalse
Iwapo masking itatumika kwenye video.
boundingbox_zipsi lazima
Ainaboolean
Chaguomsingifalse
Iwapo itarejeshwa kumbukumbu ya ZIP iliyo na viwekeleo vya visanduku vya mipaka kwa kila fremu.
detection_thresholdsi lazima
Ainanumber
Chaguomsingi0.5
0.01 – 1
Kikomo cha kujiamini cha utambuzi, chaguomsingi ikiwa 0.5 kwa vitu vilivyopo na 0.7 kwa vipya. Ndani ya masafa ya 0.0–1.0, thamani ndogo hupunguza usahihi kwa kuongeza idadi ya utambuzi; jaribu 0.2–0.3 vidokezo vya maandishi vinaposhindwa.
frame_indexsi lazima
Ainainteger
Chaguomsingi0
Faharasa ya fremu kwa mwingiliano wa awali wakati wa kutoa mask_url.
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": "sam-3/video-rle",
  "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": 95,
    "usd": "0.095",
    "charged": 95,
    "refunded": 0
  },
  "input": {
    "video_url": "https://content.doitong.com/video/showcase/v3/gen_fox_cartoon.mp4"
  },
  "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
    },
    "boundingbox_frames_zip": {
      "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
    }
  },
  "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}Video iliyozalishwa na segmentation.
boundingbox_frames_zip
object {url, content_type, file_name, file_size} | nullKumbukumbu ya ZIP ya viwekeleo vya visanduku vya mipaka kwa kila fremu.

Miundo zaidi: Video hadi Video

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/sam-3/video-rle.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt