Seedream 5.0 Pro 提供開始 | 画像ジェネレーターで試す →

NVIDIA Cosmos 3 Super Text to Image API

nvidia /

NVIDIA Cosmos 3 Super Text to Image is a fast AI image generation model that creates high-quality images from text prompts with configurable image size, inference steps, guidance, and output count. Ready-to-use REST inference API for creative design, marketing visuals, product mockups, concept art, brand assets, social media content, and professional text-to-image workflows with simple integration, no coldstarts, and affordable pricing.

text-to-image
入力

待機中

A photorealistic high-fashion portrait of an adult female model standing in a minimalist art gallery, sculptural black dress, polished concrete floor, large abstract paintings, soft museum lighting, confident elegant pose, luxury editorial photography, clean composition, ultra-detailed

$0.041回あたり·~25 / $1

次:

サンプルすべて表示

A photorealistic high-fashion portrait of an adult female model standing in a minimalist art gallery, sculptural black dress, polished concrete floor, large abstract paintings, soft museum lighting, confident elegant pose, luxury editorial photography, clean composition, ultra-detailed

A photorealistic high-fashion portrait of an adult female model standing in a minimalist art gallery, sculptural black dress, polished concrete floor, large abstract paintings, soft museum lighting, confident elegant pose, luxury editorial photography, clean composition, ultra-detailed

関連モデル

README

NVIDIA Cosmos 3 Super Text-to-Image

NVIDIA Cosmos 3 Super Text-to-Image generates high-quality images from natural-language prompts with support for negative prompting, size presets, inference step control, guidance scaling, and flexible output formats. It is suitable for portrait generation, editorial visuals, concept art, marketing creatives, and other prompt-driven image generation workflows.

Why Choose This?

  • High-quality text-to-image generation Create polished, detailed images from natural-language prompts.

  • Negative prompt support Use negative_prompt to suppress unwanted artifacts, styles, or scene elements.

  • Flexible generation controls Adjust num_inference_steps and guidance_scale to balance quality, fidelity, and generation behavior.

  • Preset sizing Use size presets for predictable output framing and composition.

  • Multiple output formats Export the result in supported formats such as jpeg.

  • Production-ready API Suitable for editorial visuals, concept exploration, commercial content, and creative ideation workflows.

Parameters

ParameterRequiredDescription
promptYesText prompt describing the image you want to generate.
negative_promptNoText description of elements or qualities you want to avoid in the result.
sizeNoOutput size preset, such as 1:1.
num_inference_stepsNoNumber of inference steps used during generation.
guidance_scaleNoControls how strongly the model follows the prompt.
output_formatNoOutput image format, such as jpeg.

How to Use

  1. Write your prompt — describe the subject, style, lighting, mood, and composition you want.
  2. Add a negative prompt (optional) — specify anything you want the model to avoid.
  3. Choose size (optional) — select the output aspect or size preset.
  4. Adjust generation settings (optional) — tune num_inference_steps and guidance_scale as needed.
  5. Choose output format (optional) — select the format that best fits your workflow.
  6. Submit — run the model and download the generated image.

Example Prompt

A photorealistic high-fashion portrait of an adult female model standing in a minimalist art gallery, sculptural black dress, polished concrete floor, large abstract paintings, soft museum lighting, confident elegant pose, luxury editorial photography, clean composition, ultra-detailed

Pricing

Just $0.04 per image.

Billing Rules

  • Each generated image costs $0.04
  • Pricing is fixed per image
  • size, num_inference_steps, guidance_scale, and output_format do not affect pricing

Best Use Cases

  • Portrait generation — Create polished editorial or studio-style portraits.
  • Fashion and luxury visuals — Generate refined commercial and magazine-style imagery.
  • Concept art — Explore visual ideas and art directions quickly.
  • Marketing creatives — Produce ad visuals, campaign concepts, and branded content.
  • Prompt-based ideation — Iterate on scenes, outfits, settings, and visual moods from text.

Pro Tips

  • Be specific in your prompt about subject, environment, lighting, and style.
  • Use negative_prompt when you want to suppress clutter, artifacts, or undesired aesthetics.
  • Increase num_inference_steps when you want more refined results, if generation time is acceptable.
  • Adjust guidance_scale when you want tighter prompt adherence.
  • Start with the default settings first, then tune generation controls only if needed.

Notes

  • prompt is required.
  • negative_prompt is optional but useful for tighter control.
  • Pricing is fixed at $0.04 per image.
  • Better prompts usually improve both consistency and visual quality.

Related Models

  • Other NVIDIA image generation workflows — Useful when you need different quality, speed, or control trade-offs.
  • Prompt-based visual generation models — Useful when you want alternate image generation styles or rendering characteristics.
注記:本サイトは第三者が提供するAIモデルを使用しています。

Cosmos 3 Super Text To Image API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/nvidia/cosmos-3-super/text-to-image with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Cosmos 3 Super Text To Image below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "size": "1:1",
    "num_inference_steps": 28,
    "guidance_scale": 4,
    "output_format": "jpeg"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/nvidia/cosmos-3-super/text-to-image" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/nvidia/cosmos-3-super/text-to-image";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "size": "1:1",
        "num_inference_steps": 28,
        "guidance_scale": 4,
        "output_format": "jpeg"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "size": "1:1",
    "num_inference_steps": 28,
    "guidance_scale": 4,
    "output_format": "jpeg"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/nvidia/cosmos-3-super/text-to-image", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Cosmos 3 Super Text To Image API — Frequently asked questions

What is the Cosmos 3 Super Text To Image API?

Cosmos 3 Super Text To Image is a NVIDIA model for image generation, exposed as a REST API on WaveSpeedAI. NVIDIA Cosmos 3 Super Text to Image is a fast AI image generation model that creates high-quality images from text prompts with configurable image size, inference steps, guidance, and output count. Ready-to-use REST inference API for creative design, marketing visuals, product mockups, concept art, brand assets, social media content, and professional text-to-image workflows with simple integration, no coldstarts, and affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Cosmos 3 Super Text To Image API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/nvidia/nvidia-cosmos-3-super-text-to-image.

How much does Cosmos 3 Super Text To Image cost per run?

Cosmos 3 Super Text To Image starts at $0.040 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Cosmos 3 Super Text To Image accept?

Key inputs: `prompt`, `size`, `guidance_scale`, `num_inference_steps`, `negative_prompt`, `output_format`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/nvidia/nvidia-cosmos-3-super-text-to-image.

How long does Cosmos 3 Super Text To Image take to generate?

Average end-to-end generation time on WaveSpeedAI is around 227 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Cosmos 3 Super Text To Image outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (NVIDIA). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

NVIDIA Cosmos 3 Super Text to Image API | WaveSpeedAI