bytedance/seedance-2.0-fast 🔢🖼️📝❓✓ → 🖼️

⭐ Official ▶️ 649.1K runs 📅 Apr 2026 ⚙️ Cog 0.18.0

image-to-video-with-audio lipsync text-to-video-with-audio video-consistent-character-generation

Performance

89.4sTypical run time

649.1KTotal runs

About

A faster variant of Seedance 2.0 for quicker video generation with multimodal inputs and native audio.

Example Output

Prompt:

"A cozy cabin in a snowy forest at night, warm light glowing from the windows, gentle snowfall, camera slowly pushing in through the trees"

Output

Performance Metrics

89.36s Prediction Time

89.37s Total Time

All Input Parameters

{
  "seed": 99,
  "prompt": "A cozy cabin in a snowy forest at night, warm light glowing from the windows, gentle snowfall, camera slowly pushing in through the trees",
  "duration": 7,
  "resolution": "720p",
  "aspect_ratio": "16:9",
  "generate_audio": true
}

Input Parameters

seed Type: integer: Random seed. Set for reproducible generation.
image Type: string: Input image for image-to-video generation (first frame). Cannot be combined with reference images.
prompt (required) Type: string: Text prompt for video generation
duration Type: integerDefault: 5Range: -1 - 15: Video duration in seconds. Set to -1 for intelligent duration (model picks the best length).
resolution Default: 720p: Video resolution.
aspect_ratio Default: 16:9: Video aspect ratio. Set to 'adaptive' to let the model choose the best ratio based on inputs.
generate_audio Type: booleanDefault: true: Generate synchronized audio with the video, including dialogue (use double quotes in prompt), sound effects, and background music.
last_frame_image Type: string: Input image for last frame generation. Only works if a first frame image is also provided. Cannot be combined with reference images.
reference_audios Type: arrayDefault:: Reference audio files (up to 3, total duration max 15s) for audio-driven generation and lip-sync. Requires at least one reference image or video. Reference them in your prompt as [Audio1], [Audio2], etc.
reference_images Type: arrayDefault:: Reference images (up to 9) for character consistency, style guidance, and scene composition. Cannot be used together with first/last frame images. You can reference them in your prompt as [Image1], [Image2], etc.
reference_videos Type: arrayDefault:: Reference videos (up to 3, total duration max 15s) for motion transfer, style reference, and editing. Reference them in your prompt as [Video1], [Video2], etc.

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Using seed: 99
Generating video...
Generated video in 86.2sec
Downloading 3248274 bytes
Downloaded 3.10MB in 2.89sec

Version Details

Version ID: 8a876cb913d631d9a4d47b3f777df7326d5571f37c49ed020fdcf4103240b158
Version Created: April 22, 2026

Run on Replicate →