Peke ki ngā ihirangi

Cosmos 3 Super Image to Video

Whakauru

id tauira nvidia/cosmos-3-super/image-to-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/nvidia/cosmos-3-super/image-to-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",
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

# 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"

Ngā kōnae pēnei i te tauira: $ 0.40 400 whiwhinga API · ≈ ₽ 43.03 ka inea ō kōnae i mua i te whakahaere Whakahaerehia ki tēnei whārangi

Tikina he kī API
NVIDIA Atahanga ki te Ataata Tukutahi Ngutu #stylized#transform#lipsync

Ka whakakorikori i tētahi whakaahua anga-tuatahi hei ataata, me te whakawhānui akiaki kōwhiringa me tētahi koromeke whakamahine ā-kaitūhura

NVIDIA · Ataata

Kei konei tō hua tuatahi

Hangaia he tono ki raro nei, ka whakahaere mā tō kī API. Ka tāruatia ngā putanga ki tō mātou rokiroki, ka puritia mō ake tonu atu, mō rānei 7 rā mō te kore utu.

Hangaia he tono

Ka hangaia ngā mana whakahaere mai i te aronuinga o te tauira. Ka whakahoungia te waehere me te utu ina whakarerekē koe.

•e hiahiatia ana 88 / 4096

Ngā tohutohu whakaputa ataata i roto i te tuhinga: tohuhia ngā mea kei te tirohanga me te nekehanga hei whakaatu.

•e hiahiatia ana image_url
Whakataka he kōnae,

Te URL atahanga hei āhuatanga mō te anga tuatahi o te ataata.

image_size taunoa {"height":480,"width"...

Ngā rahinga ataata e tonoa ana i mua i te whakatikatika aunoa. Hei whiwhi rahinga tautoko, ka whakawhāiti te pūnaha i te tono, ka kōwhiri i te taumata NVIDIA tata rawa—256p, 480p, 720p—me te ōwehenga āhuatanga tautoko.

taunoa 2

Te tepe runga mō ngā wāhanga tohutohu ina whakakāngia te whakaputanga agentic.

taunoa 2

Te tatau kaitono ataata mō ia iterenga o te koropiko agentic; ka whakatau e hia ngā ataata ka whakataetae i te aromātai i mua i te tuku i te mea pai ki te tuhi anō i te tohutohu.

taunoa 189

Te tatau anga mō te whakaputanga; mā te whakanui ka roa ake te ataata.

taunoa 24

Te tere anga ataata putanga, i ine ki ngā anga ia hēkona.

Arā atu negative_prompt · num_inference_steps · guidance_scale · seed · enable_prompt_expansion · agentic_early_stop · enable_safety_checker
0 / 2048

Te tohutohu tōraro hei whakaiti i ngā ihirangi pēnei i te nekehanga kāore e hiahiatia ana, i ngā parahanga rānei. Ki te waiho, ka whakamahia te tohutohu tōraro a NVIDIA mō i2v; ko te aho putua ka mono i te arataki tōraro.

taunoa 28

Te tatau hīkoi tango haruru, ka whakawhiti i te roa o te tukatuka mō te kounga pai ake ina whakapikihia te tatau.

taunoa 6

Te kaha o te arataki kore-whakarōpū.

Te kākano e whakahaere ana i te tukurua: ka whakaputa te tohutohu me te kākano ōrite i te ataata ōrite ina kāore te putanga tauira i rerekē.

POST /run/nvidia/cosmos-3-super/image-to-video?wait=20 utu → $ 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/nvidia/cosmos-3-super/image-to-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",
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  }'

# 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"

Whakahaerehia tēnei tono

Ka noho tō kī ki tēnei pūtirotiro: ka tukuna ki te Doitong API anake, ā, ka tiakina ki te localStorage anake ina tohua e koe te Mahara. Tikina he kī API

Mō Cosmos 3 Super Image to Video

Ka whakamahi i `image_url` hei anga tīmatanga me tētahi `prompt` kia 4096 pūāhua te mōrahi. Ka tae `num_frames` ki te 189, ā, ko `frames_per_second` mai i te 4 ki te 60. Ka whakakā taunoa te whakawhānui akiaki, ā, ka whakahaere `enable_agentic_generation` i ngā kaitono hurihuri me te arotake. Kei reira hoki `negative_prompt`, `guidance_scale` me `num_inference_steps` tae atu ki te 50.

Ngā tawhā

Tukuna te ingoa tōmua, te ingoa taketake rānei, kaua e rua. Ngā ingoa tōmua

IngoaMomo TaunoaE whakaaetia ana Whakamārama
prompte hiahiatia ana
Momostring
≤ 4,096 pūāhua
Ngā tohutohu whakaputa ataata i roto i te tuhinga: tohuhia ngā mea kei te tirohanga me te nekehanga hei whakaatu.
image_urle hiahiatia ana image
Momourl · image
Te URL atahanga hei āhuatanga mō te anga tuatahi o te ataata.
negative_promptkōwhiringa
Momostring
TaunoaThe video captures a series of frames showing macroblocking artifacts, chromatic aberration, high-frequency noise, and rolling shutter distortion. It includes static with no motion, motion blur, over-saturation, shaky footage, low resolution, grainy texture, pixelated images, poorly lit areas, underexposed and overexposed scenes, poor color balance, washed out colors, choppy sequences, jerky movements, low frame rate, bit-depth compression artifacts, color banding, unnatural transitions, outdated special effects, fake elements, unconvincing visuals, poorly edited content, jump cuts, hard cut, visual noise, and flickering. It features moiré patterns, edge halos, and temporal aliasing. Furthermore, the content defies common sense, generating illogical scenarios, nonsensical entities, absurd character behaviors, and conceptual paradoxes that violate basic human reasoning and everyday reality. The video looks like a surreal or glitchy hallucination. Overall, the video is of poor quality.
≤ 2,048 pūāhua
Te tohutohu tōraro hei whakaiti i ngā ihirangi pēnei i te nekehanga kāore e hiahiatia ana, i ngā parahanga rānei. Ki te waiho, ka whakamahia te tohutohu tōraro a NVIDIA mō i2v; ko te aho putua ka mono i te arataki tōraro.
enable_prompt_expansionkōwhiringa
Momoboolean
Taunoatrue
Te whakawhānui tohutohu, ina true, ka whakamahi i Cosmos3-Nano Reasoner hei whakaputa i te whakatakotoranga dense-caption i whakamahia hei whakangungu i Cosmos3; ka tirohia e tēnei VLM te anga tuatahi. Mā COSMOS_PROMPT_UPSAMPLER_BASE_URL e kōwhiri te ratonga Reasoner kua whirihorahia; ki te kore, ka whakarewahia e te taupānga ā-rohe. Ki te rahua te whakawhānui, ka whakamahia tonu te tohutohu kāore i whakarerekētia.
enable_agentic_generationkōwhiringa
Momoboolean
Taunoafalse
Te whakaputanga Cosmos agentic ā-iterenga, he tino pōturi ake, he nui ake te utu i te whakaputa kotahi nā te mea me tino tāpae ia kaitono. Ka whakarangatira te koropiko i te tohutohu, ka whakaputa kaitono ataata, ka whakamahi i te VLM ki te arotake i ngā anga kua tīpakohia, ā, ka tuhi anō i te tohutohu.
agentic_max_iterationskōwhiringa
Momointeger
Taunoa2
1 – 3
Te tepe runga mō ngā wāhanga tohutohu ina whakakāngia te whakaputanga agentic.
agentic_samples_per_iterationkōwhiringa
Momointeger
Taunoa2
1 – 3
Te tatau kaitono ataata mō ia iterenga o te koropiko agentic; ka whakatau e hia ngā ataata ka whakataetae i te aromātai i mua i te tuku i te mea pai ki te tuhi anō i te tohutohu.
agentic_early_stopkōwhiringa
Momoboolean
Taunoatrue
Te whakahaere whakamutu wawe e kī ana he rawaka te kaute arotake kei runga ake i te paepae kounga pūmau hei whakamutu i te koropiko agentic.
image_sizekōwhiringa
Momoobject
Taunoa{"height":480,"width":832}
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
Ngā rahinga ataata e tonoa ana i mua i te whakatikatika aunoa. Hei whiwhi rahinga tautoko, ka whakawhāiti te pūnaha i te tono, ka kōwhiri i te taumata NVIDIA tata rawa—256p, 480p, 720p—me te ōwehenga āhuatanga tautoko.
num_frameskōwhiringa
Momointeger
Taunoa189
5 – 189
Te tatau anga mō te whakaputanga; mā te whakanui ka roa ake te ataata.
frames_per_secondkōwhiringa
Momointeger
Taunoa24
4 – 60
Te tere anga ataata putanga, i ine ki ngā anga ia hēkona.
num_inference_stepskōwhiringa
Momointeger
Taunoa28
1 – 50
Te tatau hīkoi tango haruru, ka whakawhiti i te roa o te tukatuka mō te kounga pai ake ina whakapikihia te tatau.
guidance_scalekōwhiringa
Momonumber
Taunoa6
0 – 20
Te kaha o te arataki kore-whakarōpū.
seedkōwhiringa
Momointeger | null
Te kākano e whakahaere ana i te tukurua: ka whakaputa te tohutohu me te kākano ōrite i te ataata ōrite ina kāore te putanga tauira i rerekē.
enable_safety_checkerkōwhiringa
Momoboolean
Taunoatrue
Te whakahaere whakaōrite mō te atahanga me te tohutohu kua tukuna, ā, ka āhei te mono mā ngā pūkete whai mana anake. Ka tirohia ngā tono kāore he whakamanatanga ahakoa te tautuhinga.
e hiahiatia ana Ingoa tōmua, e whakaaetia ana hoki

Mō ngā tawhā kōnae, whakamahia he URL tūmatanui https://, he URI data: tae atu ki te 10 MB, he file_url rānei o tētahi tukuake. Ngā kōnae

Putanga

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "nvidia/cosmos-3-super/image-to-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",
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
  },
  "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,
      "width": 1024,
      "height": 768,
      "fps": 1.0,
      "duration": 5,
      "num_frames": 1
    },
    "seed": 42
  },
  "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.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Ō kōnae, māu e whiriwhiriKo ia url o outputs[] he tārua kei tō mātou rokiroki: ka puritia mō ake tonu atu (ka utua ia GB-marama) mō rānei 7 rā mō te kore utu, e ai ki ngā tautuhinga o tō pūkete, ki te ?storage= rānei.
He ōrite te hanga ki ia tauiratype, url, content_type, width, height me duration, mō ngā pikitia, ataata me te oro. Ko output te ahanoa hua ake o te tauira.
Ngā āpure o te putanga
video
object {url, content_type, file_name, file_size, width, height, fps, duration, num_frames}Ataata i whakaputaina e te tauira.
seed
integerTe uara kākano i whakamahia i te whakaputanga.

Ētahi atu tauira: Atahanga ki te Ataata

Mō ngā āpiha AI: kei te wātea tēnei whārangi hei Markdown ki https://doitong.com/mi/developers/models/nvidia/cosmos-3-super/image-to-video.md. Ngā tauira me ngā aratohu katoa: https://doitong.com/developers/llms.txt