Nemotron Diffusion Vlm

Unganisha

Kitambulisho cha modeli nemotron-diffusion-vlm

# 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/nemotron-diffusion-vlm?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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/nemotron-diffusion-vlm?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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 = {
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nemotron-diffusion-vlm", 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": "nemotron-diffusion-vlm",
  "input": {
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }
}

Piga modeli ya Nemotron Diffusion Vlm (nemotron-diffusion-vlm) kupitia Doitong API. Nyaraka za mawakala: https://doitong.com/sw/developers/models/nemotron-diffusion-vlm.md

POST https://api.doitong.ru/v1/run/nemotron-diffusion-vlm?wait=20
Authorization: Bearer $DOITONG_API_KEY
Content-Type: application/json

{
  "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
  "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
}

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/nemotron-diffusion-vlm yenye mwili uleule hurejesha bei kamili kabla ya kuendesha.

Ombi hili: ≈$ 0.005 salio za API 5 · ≈ ₽ 0.53 Iendeshe kwenye ukurasa huu

Pata ufunguo wa API

NVIDIA Maono #utility#editing

Modeli ya maono na lugha inayojibu vidokezo kuhusu picha kwa kutumia usimbaji wa maandishi unaotegemea diffusion

OpenAPI Markdown

NVIDIA · 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.

prompt •inahitajika

Kidokezo kinachobainisha cha kujibu kuhusu picha.

image •inahitajika image_url

Dondosha faili, au

URL inayoelekeza kwenye picha ya kuchakatwa.

Ya kina max_tokens · num_inference_steps · block_length · threshold · enable_safety_checker

max_tokens chaguomsingi 512

Kikomo cha juu cha tokeni zinazozalishwa.

num_inference_steps chaguomsingi 256

Chagua idadi ya hatua za usimbuaji wa diffusion iwe kizidisho cha max_tokens / block_length unapoiainisha wazi; idadi hiyo pia isiwe ndogo kuliko mgawo huo.

block_length chaguomsingi 32

Urefu wa kila kizuizi cha usimbuaji wa diffusion.

threshold chaguomsingi 0.9

Kikomo cha kujiamini kwa usimbuaji wa diffusion.

POST /run/nemotron-diffusion-vlm?wait=20 makadirio → $ 0.005

# 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/nemotron-diffusion-vlm?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }'

# 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/nemotron-diffusion-vlm?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  }),
});
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 = {
    "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/nemotron-diffusion-vlm", 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": "nemotron-diffusion-vlm",
      "input": {
        "image": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
        "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
      },
      "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 Nemotron Diffusion Vlm

Hupokea picha katika `image_url` na swali katika `prompt`, kisha kurudisha jibu la maandishi. Usimbaji unaweza kurekebishwa kupitia `max_tokens` (1 hadi 8192), `num_inference_steps` (1 hadi 1024), `block_length` (8 hadi 128) na `threshold` ya uaminifu kutoka 0 hadi 1. Matokeo pia yanajumuisha maelezo ya muda na matumizi.

Vigezo

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

JinaAina ChaguomsingiInaruhusiwa Maelezo

image_urlinahitajika image

Ainaurl · image

URL inayoelekeza kwenye picha ya kuchakatwa.

promptinahitajika

Ainastring

Kidokezo kinachobainisha cha kujibu kuhusu picha.

max_tokenssi lazima

Ainainteger

Chaguomsingi512

1 – 8,192

Kikomo cha juu cha tokeni zinazozalishwa.

num_inference_stepssi lazima

Ainainteger | null

Chaguomsingi256

1 – 1,024

Chagua idadi ya hatua za usimbuaji wa diffusion iwe kizidisho cha max_tokens / block_length unapoiainisha wazi; idadi hiyo pia isiwe ndogo kuliko mgawo huo.

block_lengthsi lazima

Ainainteger

Chaguomsingi32

8 – 128

Urefu wa kila kizuizi cha usimbuaji wa diffusion.

thresholdsi lazima

Ainanumber

Chaguomsingi0.9

0 – 1

Kikomo cha kujiamini kwa usimbuaji wa diffusion.

enable_safety_checkersi lazima

Ainaboolean

Chaguomsingitrue

Ukaguzi unaweza kulegezwa kwa kuweka false, ikiwa mpigaji simu ameidhinishwa.

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": "nemotron-diffusion-vlm",
  "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": 5,
    "usd": "0.005",
    "charged": 5,
    "refunded": 0
  },
  "input": {
    "image_url": "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg",
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field"
  },
  "output": {
    "output": "The image shows a dog sitting outdoors.",
    "usage": {
      "prompt_tokens": 1,
      "completion_tokens": 1,
      "num_function_evals": 1
    },
    "timings": {
      "total_time": 1.0,
      "image_validation_time": 1.0,
      "preprocessing_time": 1.0,
      "gpu_transfer_time": 1.0,
      "generation_time": 1.0,
      "decode_time": 1.0
    }
  },
  "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: stringJibu lililozalishwa na modeli.
usage: object {prompt_tokens, completion_tokens, num_function_evals}Maelezo ya matumizi ya tokeni na usimbuaji wa diffusion.
timings: object {total_time, image_validation_time, preprocessing_time, gpu_transfer_time, generation_time, decode_time}Mgawanyo wa nyakati za kuchakata ombi, kwa sekunde.

Kwa mawakala wa AI: ukurasa huu katika Markdown unapatikana kwenye https://doitong.com/sw/developers/models/nemotron-diffusion-vlm.md. Modeli na miongozo yote: https://doitong.com/developers/llms.txt

Tokeo lako la kwanza linaonekana hapa

Unda ombi

Endesha ombi hili

Kuhusu Nemotron Diffusion Vlm

Vigezo

Tokeo

Miundo zaidi: Maono

Nemotron 3 Nano Omni · Video Tofauti: 4

Nemotron 3 Nano Omni · Vision Tofauti: 4

NVIDIA Nemotron 3.5 Super Video Tofauti: 3

NVIDIA Nemotron 3.5 Super Vision Tofauti: 3