Cosmos 3 Super Image to Video

Unganisha

Kitambulisho cha modeli 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"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/nvidia/cosmos-3-super/image-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nvidia/cosmos-3-super/image-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

# 1. Connect once (Claude Code; Cursor, VS Code, Claude Desktop: https://doitong.com/sw/developers/docs/mcp)
claude mcp add --transport http doitong-models https://api.doitong.ru/v1/mcp \
  --header "Authorization: Bearer $DOITONG_API_KEY"

# 2. Your agent calls the "run" tool with:
{
  "model_id": "nvidia/cosmos-3-super/image-to-video",
  "input": {
    "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"
  }
}

Piga modeli ya Cosmos 3 Super Image to Video (nvidia/cosmos-3-super/image-to-video) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/nvidia/cosmos-3-super/image-to-video.md

POST https://api.doitong.ru/v1/run/nvidia/cosmos-3-super/image-to-video?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "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"
}

Ikiwa hali ya jibu ni "queued" au "running", piga GET https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20 mara kwa mara hadi iwe "succeeded"; faili ziko kwenye outputs[].url. POST https://api.doitong.ru/v1/quote/nvidia/cosmos-3-super/image-to-video yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Faili kama mfano: $ 0.40 salio za API 400 · ≈ ₽ 42.93 faili zako hupimwa kabla ya kuendesha Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

NVIDIA Picha hadi Video Usawazishaji wa midomo #stylized#transform#lipsync

Huunda uhuishaji wa picha ya fremu ya kwanza kuwa video, ikiwa na upanuzi wa kidokezo wa hiari na mzunguko wa uboreshaji wa kiwakala

OpenAPI Markdown

NVIDIA · 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

Bei kwa kila sekunde ya video yako ya kutolewa

Bei kulingana na uingizaji wako

kuanzia $ 0.05 / sekunde ya video ya tokeo

salio za API 50 / sekunde ya video ya tokeo · ≈ ₽ 5.37

Ombi hili: sekunde 8 × $ 0.05 $ 0.40 salio za API 400 · ≈ ₽ 42.93

Endesha · $ 0.40

Hutozwa tu ikifanikiwa, na kurejeshewa kiotomatiki ikishindwa.

agentic_max_iterations chaguomsingi 2

agentic_samples_per_iteration chaguomsingi 2

Faili zako hupimwa kabla ya kuendeshwa (urefu, mwonekano, kasi ya fremu); makadirio hurejesha bei kamili na uendeshaji hutozwa kiasi hicho hicho.

Endpoint ya makadirio: POST /quote/{id}

Unda ombi

Vidhibiti vinazalishwa kutoka kwenye schema ya modeli. Msimbo na bei husasishwa unapovibadilisha.

prompt •inahitajika 88 / 4096

Maelekezo ya uzalishaji wa video kwa maandishi: bainisha mandhari iliyomo na mwendo unaopaswa kuonyesha.

image •inahitajika image_url

Dondosha faili, au

URL ya picha inayotumika kuweka fremu ya kwanza ya video.

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

Vipimo vya video vinavyoombwa kabla ya marekebisho ya kiotomatiki. Ili kupata ukubwa unaotumika, mfumo hupunguza ombi na kuchagua daraja la karibu zaidi la NVIDIA—256p, 480p au 720p—na uwiano wa picha unaotumika.

agentic_max_iterations chaguomsingi 2

Kikomo cha juu cha hatua za kidokezo wakati uzalishaji wa kiwakala umewezeshwa.

agentic_samples_per_iteration chaguomsingi 2

Idadi ya wagombea wa video kwa kila marudio katika mzunguko wa kiwakala, ikibainisha video ngapi hushindana katika tathmini kabla bora kuendelea kwenye uandikaji upya wa kidokezo.

num_frames chaguomsingi 189

Idadi ya fremu za uzalishaji; kuiongeza huzalisha video ndefu zaidi.

frames_per_second chaguomsingi 24

Kiwango cha fremu cha video ya tokeo, kinachopimwa kwa fremu kwa sekunde.

Ya kina negative_prompt · num_inference_steps · guidance_scale · seed · enable_prompt_expansion · agentic_early_stop · enable_safety_checker

negative_prompt 0 / 2048

Kidokezo hasi cha kuzuia maudhui kama mwendo au vizalia visivyotakiwa. Kukiacha hutumia kidokezo hasi kinachopendekezwa na NVIDIA kwa i2v, huku mfuatano tupu ukizima mwongozo hasi.

num_inference_steps chaguomsingi 28

Idadi ya hatua za kuondoa kelele, ambapo uchakataji mrefu zaidi huleta ubora bora kadiri idadi inavyoongezeka.

guidance_scale chaguomsingi 6

Nguvu ya mwongozo usio na klasifaya.

seed

Mbegu inayodhibiti urudiwaji: kidokezo na mbegu zinazofanana huzalisha video inayofanana wakati toleo la modeli halijabadilika.

POST /run/nvidia/cosmos-3-super/image-to-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/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"

const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/nvidia/cosmos-3-super/image-to-video?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "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"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");

import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "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",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nvidia/cosmos-3-super/image-to-video", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "nvidia/cosmos-3-super/image-to-video",
      "input": {
        "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"
      },
      "wait_seconds": 20
    }
  }
}

Endesha ombi hili

Ufunguo wa API

Key yako inabaki kwenye kivinjari hiki: inatumwa kwa Doitong API pekee na kuhifadhiwa (localStorage) tu ukiweka tiki kwenye Kumbuka. Kumbuka katika kivinjari hiki Pata ufunguo wa API

Kuhusu Cosmos 3 Super Image to Video

Hutumia `image_url` kama fremu ya mwanzo na `prompt` yenye hadi vibambo 4096. `num_frames` hufikia 189 na `frames_per_second` ni kuanzia 4 hadi 60. Upanuzi wa kidokezo umewashwa kwa chaguomsingi, na `enable_agentic_generation` huendesha watahiniwa wa marudio pamoja na uhakiki. Pia hutoa `negative_prompt`, `guidance_scale` na `num_inference_steps` hadi 50.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo

promptinahitajika

Ainastring

≤ herufi 4,096

Maelekezo ya uzalishaji wa video kwa maandishi: bainisha mandhari iliyomo na mwendo unaopaswa kuonyesha.

image_urlinahitajika image

Ainaurl · image

URL ya picha inayotumika kuweka fremu ya kwanza ya video.

negative_promptsi lazima

Ainastring

ChaguomsingiThe 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.

≤ herufi 2,048

Kidokezo hasi cha kuzuia maudhui kama mwendo au vizalia visivyotakiwa. Kukiacha hutumia kidokezo hasi kinachopendekezwa na NVIDIA kwa i2v, huku mfuatano tupu ukizima mwongozo hasi.

enable_prompt_expansionsi lazima

Ainaboolean

Chaguomsingitrue

Upanuzi wa kidokezo ambao ukiwa true hutumia Cosmos3-Nano Reasoner kutengeneza umbizo la maelezo mnene linalotumika kufunza Cosmos3; VLM hii huchunguza fremu ya kwanza. COSMOS_PROMPT_UPSAMPLER_BASE_URL huchagua huduma ya Reasoner iliyosanidiwa; la sivyo programu huanzisha moja ndani ya mfumo. Kushindwa kwa upanuzi huacha kidokezo kisichobadilishwa kitumike.

enable_agentic_generationsi lazima

Ainaboolean

Chaguomsingifalse

Uzalishaji wa kiwakala wa Cosmos unaorudiwa, ambao ni wa polepole na wa gharama zaidi kuliko kuzalisha mara moja kwa sababu kila mgombea huhitaji uonyeshaji kamili. Mzunguko hupanua kidokezo, huzalisha wagombea wa video, hutumia VLM kukosoa fremu zilizochaguliwa na kuandika upya kidokezo.

agentic_max_iterationssi lazima

Ainainteger

Chaguomsingi2

1 – 3

Kikomo cha juu cha hatua za kidokezo wakati uzalishaji wa kiwakala umewezeshwa.

agentic_samples_per_iterationsi lazima

Ainainteger

Chaguomsingi2

1 – 3

Idadi ya wagombea wa video kwa kila marudio katika mzunguko wa kiwakala, ikibainisha video ngapi hushindana katika tathmini kabla bora kuendelea kwenye uandikaji upya wa kidokezo.

agentic_early_stopsi lazima

Ainaboolean

Chaguomsingitrue

Udhibiti wa kusitisha mapema unaochukulia alama ya mkosoaji iliyo juu ya kizingiti kali cha ubora kuwa ya kutosha kumaliza mzunguko wa kiwakala.

image_sizesi lazima

Ainaobject

Chaguomsingi{"height":480,"width":832}

square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9

num_framessi lazima

Ainainteger

Chaguomsingi189

5 – 189

Idadi ya fremu za uzalishaji; kuiongeza huzalisha video ndefu zaidi.

frames_per_secondsi lazima

Ainainteger

Chaguomsingi24

4 – 60

Kiwango cha fremu cha video ya tokeo, kinachopimwa kwa fremu kwa sekunde.

num_inference_stepssi lazima

Ainainteger

Chaguomsingi28

1 – 50

Idadi ya hatua za kuondoa kelele, ambapo uchakataji mrefu zaidi huleta ubora bora kadiri idadi inavyoongezeka.

guidance_scalesi lazima

Ainanumber

Chaguomsingi6

0 – 20

Nguvu ya mwongozo usio na klasifaya.

seedsi lazima

Ainainteger | null

Mbegu inayodhibiti urudiwaji: kidokezo na mbegu zinazofanana huzalisha video inayofanana wakati toleo la modeli halijabadilika.

enable_safety_checkersi lazima

Ainaboolean

Chaguomsingitrue

Udhibiti wa usimamizi wa maudhui kwa picha na kidokezo kilichotolewa, huku kuzima kukiruhusiwa tu kwa akaunti zilizoidhinishwa. Maombi yasiyo na idhini hukaguliwa bila kujali mpangilio huo.

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": "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"
  }
}

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, width, height, fps, duration, num_frames}Video iliyozalishwa na modeli.
seed: integerThamani ya seed inayotumika wakati wa uzalishaji.