zsxkib/seedance-1-with-sound
bytedance/seedance-1-(lite/pro) + topazlabs/video-upscale + zsxkib/smart-thinksound
Public
80
runs
Run zsxkib/seedance-1-with-sound with an API
Use one of our client libraries to get started quickly. Clicking on a library will take you to the Playground tab where you can tweak different inputs, see the results, and copy the corresponding code to use in your own project.
Input schema
The fields you can use to run this model with an API. If you don't give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| model_quality |
None
|
lite
|
Video generation model: 'lite' [bytedance/seedance-1-lite] for faster generation with last frame support (480p-720p), 'pro' [bytedance/seedance-1-pro] for higher quality (480p-1080p)
|
| prompt |
string
|
[seedance-1-lite/pro] Text prompt for video generation
|
|
| image |
string
|
[seedance-1-lite/pro] Input image for image-to-video generation (both models)
|
|
| last_frame_image |
string
|
[seedance-1-lite only] Input image for last frame generation. Auto-switches to lite model when provided. Requires 'image' parameter to be set as start frame.
|
|
| duration |
None
|
5
|
[seedance-1-lite/pro] Video duration in seconds (both models)
|
| resolution |
None
|
720p
|
[seedance-1-lite/pro] Video resolution. 480p: both models, 720p: lite only (default), 1080p: pro only (default)
|
| aspect_ratio |
None
|
16:9
|
[seedance-1-lite/pro] Video aspect ratio. Ignored if an image is used (both models)
|
| camera_fixed |
boolean
|
False
|
[seedance-1-lite/pro] Whether to fix camera position (both models)
|
| seed |
integer
|
[seedance-1-lite/pro] Random seed for reproducible generation (both models)
|
|
| enable_sound |
boolean
|
True
|
Enable AI-generated sound effects and ambient audio
|
| context_hint |
string
|
|
[zsxkib/smart-thinksound] Optional context hint for better audio generation (e.g., 'fireworks video', 'cat playing', 'machinery sounds')
|
| enable_upscaling |
boolean
|
True
|
Enable video upscaling for enhanced resolution and frame rate
|
| target_resolution |
None
|
1080p
|
[topazlabs/video-upscale] Target resolution for upscaling
|
| target_fps |
integer
|
60
Min: 15 Max: 120 |
[topazlabs/video-upscale] Target frame rate for upscaling (15-120 fps)
|
{
"type": "object",
"title": "Input",
"required": [
"prompt"
],
"properties": {
"seed": {
"type": "integer",
"title": "Seed",
"x-order": 8,
"description": "[seedance-1-lite/pro] Random seed for reproducible generation (both models)"
},
"image": {
"type": "string",
"title": "Image",
"x-order": 2,
"description": "[seedance-1-lite/pro] Input image for image-to-video generation (both models)"
},
"prompt": {
"type": "string",
"title": "Prompt",
"x-order": 1,
"description": "[seedance-1-lite/pro] Text prompt for video generation"
},
"duration": {
"enum": [
5,
10
],
"type": "integer",
"title": "duration",
"description": "[seedance-1-lite/pro] Video duration in seconds (both models)",
"default": 5,
"x-order": 4
},
"resolution": {
"enum": [
"480p",
"720p",
"1080p"
],
"type": "string",
"title": "resolution",
"description": "[seedance-1-lite/pro] Video resolution. 480p: both models, 720p: lite only (default), 1080p: pro only (default)",
"default": "720p",
"x-order": 5
},
"target_fps": {
"type": "integer",
"title": "Target Fps",
"default": 60,
"maximum": 120,
"minimum": 15,
"x-order": 13,
"description": "[topazlabs/video-upscale] Target frame rate for upscaling (15-120 fps)"
},
"aspect_ratio": {
"enum": [
"16:9",
"4:3",
"1:1",
"3:4",
"9:16",
"21:9",
"9:21"
],
"type": "string",
"title": "aspect_ratio",
"description": "[seedance-1-lite/pro] Video aspect ratio. Ignored if an image is used (both models)",
"default": "16:9",
"x-order": 6
},
"camera_fixed": {
"type": "boolean",
"title": "Camera Fixed",
"default": false,
"x-order": 7,
"description": "[seedance-1-lite/pro] Whether to fix camera position (both models)"
},
"context_hint": {
"type": "string",
"title": "Context Hint",
"default": "",
"x-order": 10,
"description": "[zsxkib/smart-thinksound] Optional context hint for better audio generation (e.g., 'fireworks video', 'cat playing', 'machinery sounds')"
},
"enable_sound": {
"type": "boolean",
"title": "Enable Sound",
"default": true,
"x-order": 9,
"description": "Enable AI-generated sound effects and ambient audio"
},
"model_quality": {
"enum": [
"lite",
"pro"
],
"type": "string",
"title": "model_quality",
"description": "Video generation model: 'lite' [bytedance/seedance-1-lite] for faster generation with last frame support (480p-720p), 'pro' [bytedance/seedance-1-pro] for higher quality (480p-1080p)",
"default": "lite",
"x-order": 0
},
"enable_upscaling": {
"type": "boolean",
"title": "Enable Upscaling",
"default": true,
"x-order": 11,
"description": "Enable video upscaling for enhanced resolution and frame rate"
},
"last_frame_image": {
"type": "string",
"title": "Last Frame Image",
"x-order": 3,
"description": "[seedance-1-lite only] Input image for last frame generation. Auto-switches to lite model when provided. Requires 'image' parameter to be set as start frame."
},
"target_resolution": {
"enum": [
"1080p",
"2k",
"4k"
],
"type": "string",
"title": "target_resolution",
"description": "[topazlabs/video-upscale] Target resolution for upscaling",
"default": "1080p",
"x-order": 12
}
}
}
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{
"type": "string",
"title": "Output",
"format": "uri"
}
Example API response
View prediction
'https://replicate.delivery/xezq/5iTbONbICe31UqyimmMjufCLa9vpfgV8urwzoYJ0hJjzfBIUB/tmpvd2bie4g.mp4'