Seedance 2.0 : Fast Tier Image to Video API
ByteDance's most advanced image-to-video model, available on fal as bytedance/seedance-2.0/fast/image-to-video.
Overview
Provide a starting image URL and a text prompt describing the desired motion. The model preserves the visual content of your image and animates it — with cinematic camera control, realistic physics, and synchronized audio all included.
Key capabilities:
- Native audio generation: music, SFX, and dialogue at no extra cost
- Director-level camera control: dolly zooms, tracking shots, POV switches, rack focuses
- Realistic physics: weight, collisions, fabric, and character motion
- Multi-shot cuts possible within a single generation, up to 15 seconds
- Start-and-end frame control: provide both a starting and ending image and the model transitions between them
- Cinematic output at 720p
| Parameter | Required | Type | Description |
|---|
prompt | Yes | string | Text describing the desired motion and action |
image_url | Yes | string | Starting frame to animate. JPEG, PNG, WebP, max 30 MB |
end_image_url | No | string | Optional ending frame. When provided, the video transitions from start to end image |
Parameters
| Parameter | Type | Default | Description |
|---|
resolution | enum | 720p | 480p (faster/cheaper) or 720p |
duration | enum | auto | auto or any integer from 4 to 15 seconds |
aspect_ratio | enum | auto | auto (inferred from input image), 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 |
generate_audio | boolean | true | Synchronized audio: SFX, ambient sound, lip-synced speech |
seed | integer | — | Fix for reproducibility (minor variation may still occur) |
end_user_id | string | — | Optional identifier for the end user |
Pricing
Billed per second of generated 720p output:
| Tier | Rate |
|---|
| Fast tier | $0.2419 / sec |
| Standard tier | $0.3024 / sec |
| Token-based billing | $0.014 / 1,000 tokens |
Token formula: tokens = (height × width × duration × 24) / 1024
A 10-second fast clip costs approximately $2.42, versus ~$3.03 on standard.
Quick Start
Python
pip install fal-client
export FAL_KEY="YOUR_API_KEY"
import fal_client
result = fal_client.subscribe(
"bytedance/seedance-2.0/fast/image-to-video",
arguments={
"prompt": "The cat slowly turns its head and blinks, fur ruffling in a gentle breeze.",
"image_url": "https://your-host.com/cat.jpg",
"resolution": "720p",
"duration": "auto",
"aspect_ratio": "auto",
"generate_audio": True,
},
with_logs=True,
on_queue_update=lambda u: [print(l["message"]) for l in u.logs]
if isinstance(u, fal_client.InProgress) else None,
)
print(result["video"]["url"])
With start and end frames:
result = fal_client.subscribe(
"bytedance/seedance-2.0/fast/image-to-video",
arguments={
"prompt": "The sun sets behind the mountains, sky shifting from gold to deep purple.",
"image_url": "https://your-host.com/golden-hour.jpg",
"end_image_url": "https://your-host.com/twilight.jpg",
"duration": "8",
"aspect_ratio": "16:9",
},
)
JavaScript / Node.js
npm install @fal-ai/client
export FAL_KEY="YOUR_API_KEY"
import { fal } from "@fal-ai/client";
const result = await fal.subscribe("bytedance/seedance-2.0/fast/image-to-video", {
input: {
prompt: "The cat slowly turns its head and blinks, fur ruffling in a gentle breeze.",
image_url: "https://your-host.com/cat.jpg",
resolution: "720p",
duration: "auto",
aspect_ratio: "auto",
generate_audio: true,
},
logs: true,
onQueueUpdate: (update) => {
if (update.status === "IN_PROGRESS") {
update.logs.map((log) => log.message).forEach(console.log);
}
},
});
console.log(result.data.video.url);
Output
{
"video": {
"url": "https://...",
"content_type": "video/mp4",
"file_name": "output.mp4",
"file_size": 4823041
},
"seed": 42
}
Async / Queue Usage
For longer generations, submit to the queue and poll:
handler = fal_client.submit(
"bytedance/seedance-2.0/fast/image-to-video",
arguments={...},
webhook_url="https://your-server.com/webhook",
)
request_id = handler.request_id
status = fal_client.status("bytedance/seedance-2.0/fast/image-to-video", request_id, with_logs=True)
result = fal_client.result("bytedance/seedance-2.0/fast/image-to-video", request_id)
Fast vs. Standard Tier
The fast tier uses the exact same schema and parameters as bytedance/seedance-2.0/image-to-video.
| Fast | Standard |
|---|
| Endpoint | bytedance/seedance-2.0/fast/image-to-video | bytedance/seedance-2.0/image-to-video |
| Cost (10 sec) | ~$2.42 | ~$3.03 |
| Latency | Lower | Higher |
| Output quality | Same | Same |
Compared to Reference-to-Video
| Image to Video | Reference to Video |
|---|
| Starting image | 1 (required) | Up to 9 (optional) |
| Ending image | 1 (optional) | Not supported |
| Reference videos | Not supported | Up to 3 |
| Reference audio | Not supported | Up to 3 |
| Use case | Animate a single image | Multi-reference, multi-modal generation |
Use image-to-video when you have one image to animate. Use reference-to-video when you need multi-modal inputs or want to reference multiple visual assets in a single prompt.
bytedance/seedance-2.0/fast/image-to-video
