Seedream 5.0 Pro ya está aquí | Pruébalo en el Generador de Imágenes →

Seedance V1 Pro Fast Text to Video

bytedance /

Seedance V1 Pro Fast creates coherent multi-shot Text-to-Video outputs with smooth motion and strong prompt fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

text-to-video
Entrada

Inactivo

$0.06por ejecución·~16 / $1

Siguiente:

EjemplosVer todo

Massive sci-fi battle scene. Thousands of giant, heavily armed mecha robots charge across a desolate, cratered battlefield under a polluted orange sky. Explosions erupt around them. Laser fire streaks across the screen. Camera is low to the ground, emphasizing the thunderous weight and impact of their footsteps. Gritty, intense action, high detail.

A lone, rusty swing set in an empty, foggy playground at dusk. One swing begins to move back and forth *by itself*, slowly gaining momentum, creaking rhythmically. No one is visible. Unsettling, quiet horror.

Cinematic sci-fi suspense. Interior of a vast, derelict, zero-gravity space station corridor, emergency lights flickering erratically. An astronaut floats slowly, using a hand torch to illuminate the drifting debris. They approach a damaged communication console. Suddenly, the console screen crackles to life, displaying a rapid, frantic sequence of unknown alien symbols in bright red before dying again with a final spark. The astronaut freezes, their breath catching (visible condensation inside helmet), slowly turning their head towards the deep darkness at the end of the corridor, as if sensing something is now *aware* of them. Tense atmosphere, handheld camera feel, extreme shadows

Close-up on a bank of flickering security monitors in a dark control room. All screens show empty, static locations (corridors, labs). Suddenly, on *one* monitor, a distorted, glitching humanoid figure flickers into existence for a split second, then vanishes, leaving only static. The camera slowly zooms in on that specific monitor.

Cinematic suspense. Slow pan upwards following creaking wooden stairs in a dark, old house. Dust motes dance in faint moonlight from a high window. Suddenly, the distinct, elongated shadow of someone (or something) standing just out of sight falls across the top landing, lingers for a moment, then quickly retracts.

Tight two-shot inside a parked car at night, streetlights casting occasional moving shadows. A couple sits in tense silence for a moment, avoiding eye contact. One person finally speaks in a low, strained whisper: "We can't keep doing this." The other person looks out the side window, jaw clenched, and replies curtly without looking back: "I know." Focus on their restrained emotions, subtle glances, and the claustrophobic atmosphere.

Extreme close-up, suspenseful thriller. Sweating hands tremble slightly as they use wire cutters to snip a single wire (blue or red?) on a complex ticking bomb. The digital timer shows 0:01. The cutters hover hesitantly for a fraction of a second... then *SNIP*. The timer freezes instantly at 0:00. The character slumps back in relief, breathing heavily. Intense focus on hands and timer. Shallow depth of field, macro shot, extreme tension

Unsettling horror short. A character sits reading a book in a dimly lit, vintage living room. In the background, on a dusty shelf, sits an old porcelain doll with glassy eyes. The character shifts slightly. As they do, the camera subtly rack focuses to the doll. For just a split second, the doll's head seems to be *slightly* turned, its eyes now looking directly at the character. The camera quickly snaps back to the character, who shivers suddenly, feeling watched, and nervously glances over their shoulder towards the shelf, seeing nothing unusual. Creepy atmosphere, shallow depth of field, slow burn tension

Slow, drifting camera shot through the zero-gravity interior of a massive, dark, abandoned space station. Debris floats silently. Suddenly, a forgotten console flickers to life, displaying a single, cryptic alien symbol in glowing green before dying again. Eerie silence, sense of ancient mystery.

Modelos relacionados

README

Seedance V1 Pro T2V Fast

Seedance V1 Pro T2V Fast is a next-generation text-to-video model designed for coherent multi-shot storytelling, smooth camera motion, and precise prompt alignment — all while maintaining exceptional generation speed. Built on the same architecture as Seedance I2V, this version allows creators to generate cinematic videos directly from text, with seamless control over style, motion, and timing.

🌟 Key Features

  • 🧠 Intelligent Text-to-Video Understanding Accurately interprets complex scene descriptions, camera actions, and emotional tones to create visually cohesive and narratively consistent clips.

  • 🎬 Multi-Shot Coherence Generates videos with stable subject motion, perspective continuity, and environmental realism across multiple frames.

  • ⚡ High-Speed Rendering (Fast Edition) Optimized for real-time workflows — delivers 480p and 720p videos with high fidelity at nearly twice the speed of standard Seedance models.

  • 🎨 Style Fidelity & Realism Preserves artistic intent, lighting, and visual style while translating pure text into dynamic motion sequences.

  • 📸 Resolution Flexibility Choose between 480p (faster, more economical) or 720p/1080p (higher quality) depending on your creative and budget needs.

⚙️ Parameters

ParameterDescription
prompt*Text description of the scene, camera movement, and atmosphere (e.g., “A wide-angle drone shot of a futuristic city at dawn, sunlight reflecting off glass towers.”).
durationVideo length in seconds (3–10s).
resolutionChoose between 480p, 720p, and 1080p.

💰 Pricing

ResolutionPrice per secondExample (5s)Example (10s)
480p$0.012 / s$0.06$0.12
720p$0.024 / s$0.12$0.24
1080p$0.048 / s$0.24$0.48

💡 Use Cases

  • Cinematic Storytelling — Generate visually rich narrative scenes directly from text.
  • Advertising & Marketing — Produce quick, high-quality motion clips for campaigns.
  • Concept Art & Visualization — Turn creative ideas or story scripts into animated previews.
  • Education & Training — Convert instructional or descriptive content into engaging visual explainers.
Nota:Este sitio web utiliza modelos de IA proporcionados por terceros.

Seedance v1 Pro Fast Text To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/bytedance/seedance-v1-pro-fast/text-to-video 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 Seedance v1 Pro Fast Text To Video 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",
    "resolution": "480p",
    "duration": 5,
    "aspect_ratio": "16:9",
    "camera_fixed": false,
    "seed": -1
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-v1-pro-fast/text-to-video" \
  -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/bytedance/seedance-v1-pro-fast/text-to-video";
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 ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "resolution": "480p",
        "duration": 5,
        "aspect_ratio": "16:9",
        "camera_fixed": false,
        "seed": -1
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${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",
    "resolution": "480p",
    "duration": 5,
    "aspect_ratio": "16:9",
    "camera_fixed": False,
    "seed": -1
}

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/bytedance/seedance-v1-pro-fast/text-to-video", 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)

Seedance v1 Pro Fast Text To Video API — Frequently asked questions

What is the Seedance v1 Pro Fast Text To Video API?

Seedance v1 Pro Fast Text To Video is a ByteDance model for video generation, exposed as a REST API on WaveSpeedAI. Seedance V1 Pro Fast creates coherent multi-shot Text-to-Video outputs with smooth motion and strong prompt fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Seedance v1 Pro Fast Text To Video 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/bytedance/bytedance-seedance-v1-pro-fast-text-to-video.

How much does Seedance v1 Pro Fast Text To Video cost per run?

Seedance v1 Pro Fast Text To Video starts at $0.060 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 Seedance v1 Pro Fast Text To Video accept?

Key inputs: `prompt`, `aspect_ratio`, `resolution`, `duration`, `seed`, `camera_fixed`. 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/bytedance/bytedance-seedance-v1-pro-fast-text-to-video.

How long does Seedance v1 Pro Fast Text To Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 61 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Seedance v1 Pro Fast Text To Video outputs commercially?

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

Seedance V1 Pro Fast Text to Video | Powerful Text-to-Video API | WaveSpeedAI