Seedance 2.0 Fast Text to Video

doubao/seedance-2-0-fast/text-to-video

doubao/seedance-2-0-fast/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

Powiązane modele

Pełne parametry, schemat wyjścia i aktualne ceny

Rynek API modeli AIJedna platforma do wszystkiegoNajpopularniejszyRegulaminPrzeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
prompt *Prompttextarea——
generate_audioGenerate Audiobooleantrue—
resolutionResolutionselect720p480p | 720p
ratioAspect Ratioselectadaptiveadaptive | 16:9 | 4:3 | 1:1 | 3:4 | 9:16 | 21:9
duration *Duration (Seconds)select54 | 5 | 6 | 7 | 8 | 9 | 10 | 11 | …
watermarkAdd Watermarkbooleanfalse—
seedSeednumber-1-1 ~ 4294967295

Pełne parametry, schemat wyjścia i aktualne ceny

Dowiedz się więcejJedna platforma do wszystkiegoPrzeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.
videosarray<string>

API

Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedance-2-0-fast/text-to-video" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": {
    "prompt": "A serene landscape with a futuristic city in the background, glowing with neon lights under a starry night sky.",
    "generate_audio": true,
    "resolution": "720p",
    "ratio": "16:9",
    "duration": 6,
    "watermark": false,
    "seed": -1
  }
}'

# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
  -H "Authorization: Bearer YOUR_API_KEY"
Python
import time, requests

API_KEY = "YOUR_API_KEY"
HEADERS = {"Authorization": f"Bearer {API_KEY}"}

# 1) Submit
resp = requests.post(
    "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedance-2-0-fast/text-to-video",
    headers=HEADERS,
    json={
        "input": {
            "prompt": "A serene landscape with a futuristic city in the background, glowing with neon lights under a starry night sky.",
            "generate_audio": True,
            "resolution": "720p",
            "ratio": "16:9",
            "duration": 6,
            "watermark": False,
            "seed": -1
        }
    },
)
resp.raise_for_status()  # 401/402/429/5xx stop here instead of polling a bad task
task = resp.json()

# 2) Poll until a terminal state (completed / failed / cancelled).
#    This model is allowed up to 300s server-side.
deadline = time.time() + 360
while task.get("status") not in ("completed", "failed", "cancelled"):
    if time.time() > deadline:
        raise TimeoutError(f"still {task.get('status')} — keep the task_uuid and poll later")
    time.sleep(3)
    poll = requests.get(f"https://www.namifusion.com/api/v1/marketplace/run/tasks/{task['task_uuid']}", headers=HEADERS)
    poll.raise_for_status()
    task = poll.json()

print(task["status"], task.get("output"))
JavaScript
const API_KEY = "YOUR_API_KEY";
const HEADERS = { Authorization: `Bearer ${API_KEY}` };

// 1) Submit
const resp = await fetch("https://www.namifusion.com/api/v1/marketplace/run/doubao/seedance-2-0-fast/text-to-video", {
  method: "POST",
  headers: { ...HEADERS, "Content-Type": "application/json" },
  body: JSON.stringify({
    "input": {
      "prompt": "A serene landscape with a futuristic city in the background, glowing with neon lights under a starry night sky.",
      "generate_audio": true,
      "resolution": "720p",
      "ratio": "16:9",
      "duration": 6,
      "watermark": false,
      "seed": -1
    }
  }),
});
if (!resp.ok) throw new Error(`submit failed: ${resp.status} ${await resp.text()}`);
let task = await resp.json();

// 2) Poll until a terminal state (completed / failed / cancelled).
//    This model is allowed up to 300s server-side.
const deadline = Date.now() + 360 * 1000;
while (!["completed", "failed", "cancelled"].includes(task.status)) {
  if (Date.now() > deadline) throw new Error(`still ${task.status} — keep the task_uuid and poll later`);
  await new Promise((r) => setTimeout(r, 3000));
  const poll = await fetch(`https://www.namifusion.com/api/v1/marketplace/run/tasks/${task.task_uuid}`, { headers: HEADERS });
  if (!poll.ok) throw new Error(`poll failed: ${poll.status}`);
  task = await poll.json();
}

console.log(task.status, task.output);

Dokumentacja API

Seedance 2.0 Fast Text to Video

A speed-optimized text-to-video model for cinematic output, native audio sync, and cost-efficient production.

Seedance 2.0 Fast Text to Video is ByteDance’s fast variant of the Seedance video generation family, designed to turn prompts into cinematic videos with native audio-visual synchronization. Built on Seed’s unified multimodal architecture, it delivers strong motion stability, prompt-driven camera and lighting control, and faster turnaround for iterative and high-volume workflows.

🚀 Key Features

  • Speed-optimized generation: Built for rapid iteration, concept testing, and faster production cycles.
  • Native audio-visual synchronization: Generates synchronized video and audio in a single pass when audio generation is enabled.
  • Director-level prompt control: Supports detailed prompting for camera movement, lighting, shadows, scene mood, and character performance.
  • Unified multimodal architecture: Works with text prompts and optional image, video, and audio references for stronger creative guidance.
  • Strong motion stability: Produces coherent subject motion and smoother transitions across short-form video sequences.
  • Cost-efficient for scale: Well suited to high-volume generation, experimentation, and A/B testing workflows.

🛠️ Technical Specifications

ItemDetails
Model architectureSeed unified multimodal architecture, speed-optimized variant
Model typeText-to-Video
InputPrompt, reference images, reference videos, reference audios
Output FormatVideo with optional native synchronized Audio
Aspect Ratio16:9, 9:16, 4:3, 3:4, 1:1, 21:9
Resolution480p, 720p, 1080p
Duration4–15 seconds (default: 5)
Audio generationSupported, enabled by default
Reference video limitTotal reference video length must not exceed 15 seconds
Reference audio limitTotal reference audio length must not exceed 15 seconds
Real-time informationOptional web search support
LatencyOptimized for fast generation; actual latency depends on resolution, duration, and reference inputs
Workflow modePrompt-only generation or reference-guided generation

Sample Prompts

  • A futuristic city street at dusk after rain, neon reflections on the pavement, slow forward camera movement, a character in a black coat walking through the crowd, cinematic lighting, tense and mysterious mood.
  • A luxury perfume commercial, close-up of water droplets on a glass bottle, soft side lighting, slow rotating camera, minimal background, premium visual style, elegant ambient sound.
  • A sunrise aerial shot over a tropical coastline, the camera rises from the ocean and reveals palm trees and a bright beach, natural colors, relaxed vacation atmosphere.

💰 Pricing

Service TypePriceEstimated Cost
Video Gen (T2V/I2V)$5.6 / 1M Tokens~$0.0538/$0.121 per second
Video Gen (V2V)$3.3 / 1M Tokens~$0.0317/$0.0713 per second

💡 Best Use Cases

  • Social media content: Generate short-form videos quickly for vertical, square, or widescreen publishing.
  • Advertising and e-commerce testing: Produce multiple creative variations for campaign testing, product storytelling, and conversion experiments.
  • Previsualization and concept development: Explore shot design, lighting direction, and scene mood before full production.
  • High-volume content pipelines: Ideal for studios, marketing teams, and platforms that need scalable video generation.

🔗 Related Models

  • Seedance 2.0 Text-to-Video: Standard version for higher-end final quality.
  • Seedance 2.0 Fast Image-to-Video: Fast image-guided video generation for workflows built around key visual references.
  • Seedance 2.0 Image-to-Video: Standard image-to-video version for higher-quality output.

Powiązane modele

xAI Grok Imagine Video v1.5 Text to Video
Tekst na wideoX Ai

xAI Grok Imagine Video v1.5 Text to Video

x-ai/grok-imagine-video-v1.5/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.840 / za uruchomienie
MiniMax H3 Text to Video
Tekst na wideoMinimax

MiniMax H3 Text to Video

minimax/h3/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.650 / za uruchomienie
ltx-2.5/text-to-video
Tekst na wideoLtx 2.5

ltx-2.5/text-to-video

ltx-2.5/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.500 / za uruchomienie
Kling Omni Video O3 Standard Text-To-Video
Tekst na wideoKling

Kling Omni Video O3 Standard Text-To-Video

kwaivgi/kling-video-o3/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.420 / za uruchomienie
Kling 3.0
Tekst na wideoKling

Kling 3.0

kwaivgi/kling-v3.0/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.420 / za uruchomienie
Kling V2.6 Text to Video API
Tekst na wideoKling

Kling V2.6 Text to Video API

kwaivgi/kling-v2.6/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.210 / za uruchomienie
Gemini Omni Flash Text to Video API
Tekst na wideoGoogle

Gemini Omni Flash Text to Video API

google/gemini-omni-flash/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $1.04 / za uruchomienie
Seedance 2.0 Mini Text to Video
Tekst na wideoDoubao

Seedance 2.0 Mini Text to Video

doubao/seedance-2.0-mini/text-to-video. Przeglądaj API modeli obrazu, wideo i zamiany twarzy. Wypróbuj model, a następnie zintegruj go przez wspólne REST API.

od $0.378 / za uruchomienie