Seedance 2.0 Mini Text to Video
doubao/seedance-2.0-mini/text-to-video
doubao/seedance-2.0-mini/text-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
相關模型
完整參數參考、輸出結構與即時價格
| AI 模型 API 市集 | 一個平台,全部完成 | 最受歡迎 | 服務條款 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|---|---|
| prompt *Prompt | textarea | — | ≤ 5000 chars | |
| ratioAspect Ratio | select | 16:9 | 16:9 | 9:16 | 4:3 | 3:4 | 1:1 | 21:9 | |
| resolutionResolution | select | 720p | 480p | 720p | |
| durationDuration | slider | 5 | 4 ~ 15 · step 1 | |
| generate_audioGenerate Audio | boolean | true | — | |
| enable_web_searchEnable Web Search | boolean | false | — | |
| return_last_framereturn the last frame | boolean | — | — |
完整參數參考、輸出結構與即時價格
| 深入了解 | 一個平台,全部完成 | 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。 |
|---|---|---|
| id | string | |
| videos | array<string> |
API
瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
cURL
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/doubao/seedance-2.0-mini/text-to-video" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "A tranquil mountain lake at sunrise, golden light crossing the water, drifting mist, slow cinematic camera movement, photorealistic.",
"ratio": "16:9",
"resolution": "720p",
"duration": 5,
"generate_audio": true,
"enable_web_search": false
}
}'
# 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-mini/text-to-video",
headers=HEADERS,
json={
"input": {
"prompt": "A tranquil mountain lake at sunrise, golden light crossing the water, drifting mist, slow cinematic camera movement, photorealistic.",
"ratio": "16:9",
"resolution": "720p",
"duration": 5,
"generate_audio": True,
"enable_web_search": False
}
},
)
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-mini/text-to-video", {
method: "POST",
headers: { ...HEADERS, "Content-Type": "application/json" },
body: JSON.stringify({
"input": {
"prompt": "A tranquil mountain lake at sunrise, golden light crossing the water, drifting mist, slow cinematic camera movement, photorealistic.",
"ratio": "16:9",
"resolution": "720p",
"duration": 5,
"generate_audio": true,
"enable_web_search": false
}
}),
});
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);API 文件
Seedance 2.0 Mini Text to Video API
A faster, lower-cost cinematic text-to-video model with native audio and up to 4K output.
Seedance 2.0 Mini Text to Video is ByteDance’s efficient text-to-video model for generating short, cinematic multi-shot sequences from natural language. It combines strong prompt adherence, AI camera control, cross-scene character consistency, flexible output formats, and native audio generation, while delivering no cold start performance and cost-effective scaling for production workloads.
🚀 Key Features
- Prompt-based video generation: Generate videos directly from natural-language prompts describing scene, action, camera movement, and mood.
- Reference-guided control: Use reference images, videos, and audio to guide visual style, character consistency, composition, motion, or sound direction.
- Cinematic multi-shot output: Optimized for narrative short-form video generation with stronger scene continuity and camera-aware storytelling.
- Native audio generation: Generate synchronized audio together with the output video to streamline post-production.
- Flexible output options: Supports multiple aspect ratios, 4–15 second durations, and 480p to 4K resolution tiers.
- Fast and production-friendly: Designed for lower cost, strong performance, and no cold starts, making it suitable for iterative creation and scaled deployment.
🛠️ Technical Specifications
| Item | Specification |
|---|---|
| Model Name | Seedance 2.0 Mini Text to Video |
| Model ID | bytedance/seedance-2.0-mini/text-to-video |
| Model Type | Text-to-video |
| Model Architecture | Multimodal conditional video generation model using text prompts |
| Input Format | Text prompt |
| Output Format | Video(optionally with synchronized native audio) |
| Prompt Guidance | Best results come from describing scene, subject, action, camera movement, lighting, and mood |
| Aspect Ratio | 16:9, 9:16, 4:3, 3:4, 1:1, 21:9 |
| Default Aspect Ratio | 16:9 |
| Resolution | 480p, 720p, 1080p, 4k |
| Default Resolution | 720p |
| Duration | 4–15 seconds |
| Default Duration | 5 seconds |
| Audio Generation | Supported, synchronized native audio enabled by default |
| Real-time Information Option | Optional web search support for prompts requiring current information |
| Performance Profile | Faster inference, lower cost, no cold start |
Sample Prompts
A cinematic night market scene, warm lantern light, people walking through a narrow street, soft camera tracking movement, steam rising from food stalls, realistic atmosphere, gentle ambient motion, rich colors, detailed urban background.A lone traveler standing on a seaside cliff at dawn, wind moving the coat, camera slowly pushing in from behind to a side close-up, pale sky, restrained but epic mood.Inside a futuristic laboratory, a humanoid robot powers on and slowly raises its head, cool lighting reflecting on metallic surfaces, low-angle orbit camera, quiet and tense atmosphere.
💰 Pricing
| Service Type | Resolution | Price |
|---|---|---|
| Video Gen (T2V/I2V) | all | $3.5 / 1M Tokens |
| Video Gen (V2V) | all | $2.1 / 1M Tokens |
Estimate Costs by Duration
| Resolution | Price per 5 seconds | Price per second |
|---|---|---|
| 480p | $0.168 | $0.0336 |
| 720p | $0.378 | $0.0756 |
| 1080p | $1.50 | $0.30 |
| 4k | $3.00 | $0.60 |
💡 Best Use Cases
- Social media content production: Create vertical, square, widescreen, or ultrawide short-form videos for platform-specific campaigns.
- Creative concepting and previs: Rapidly prototype scenes, camera moves, and mood for advertising, branded content, and film development.
- Character and style consistency workflows: Use reference images to maintain visual identity across shots and scenes.
- Audio-visual narrative clips: Generate short cinematic sequences with synchronized sound for immersive storytelling and promotional content.
🔗 Related Models
- ByteDance Seedance 2.0 Mini Image-to-Video: Better suited for workflows that begin from a starting image plus prompt.
相關模型
xAI Grok Imagine Video v1.5 Text to Video
x-ai/grok-imagine-video-v1.5/text-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
MiniMax H3 Text to Video
minimax/h3/text-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
ltx-2.5/text-to-video
ltx-2.5/text-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Kling Omni Video O3 Standard Text-To-Video
kwaivgi/kling-video-o3/text-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Kling 3.0
kwaivgi/kling-v3.0/text-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Kling V2.6 Text to Video API
kwaivgi/kling-v2.6/text-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Gemini Omni Flash Text to Video API
google/gemini-omni-flash/text-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。
Seedance 2.5 Text-to-Video
doubao/seedance-2-5/text-to-video. 瀏覽圖像、影片與換臉模型 API。先試用任一模型,再透過統一 REST API 整合。