bytedance/seedance-1-lite ❓🔢🖼️📝✓ → 🖼️

⭐ Official ▶️ 1.4M runs 📅 Jun 2025 ⚙️ Cog 0.16.8
image-to-video text-to-video video-consistent-character-generation

About

A video generation model that offers text-to-video and image-to-video support for 5s or 10s videos, at 480p and 720p resolution

Example Output

Prompt:

"a woman walks in the park"

Output

Performance Metrics

38.08s Prediction Time
38.20s Total Time
All Input Parameters 
{
  "fps": 24,
  "prompt": "a woman walks in the park",
  "duration": 5,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "camera_fixed": false
}
Input Parameters
fps Default: 24
Frame rate (frames per second)
seed Type: integer
Random seed. Set for reproducible generation
image Type: string
Input image for image-to-video generation
prompt (required) Type: string
Text prompt for video generation
duration Type: integerDefault: 5Range: 3 - 12
Video duration in seconds
resolution Default: 720p
Video resolution
aspect_ratio Default: 16:9
Video aspect ratio. Ignored if an image is used.
camera_fixed Type: booleanDefault: false
Whether to fix camera position
last_frame_image Type: string
Input image for last frame generation. This only works if an image start frame is given too.
reference_images Type: array
Reference images (1-4 images) to guide video generation for characters, avatars, clothing, environments, or multi-character interactions. Reference images cannot be used with 1080p resolution or first frame or last frame images.
Output Schema

Output

Type: string • Format: uri

Example Execution Logs 
Using seed: 839963121
Generating video...
Generated video in 28.2sec
Downloading 3945017 bytes
Downloaded 3.76MB in 9.87sec
Total tokens used: 103818
Version Details
Version ID
754204783e134ee20a3f3c152d1519132ab93d237bfdadba587ed585ffe9fcfd
Version Created
October 13, 2025
Run on Replicate →