← Back to all generators
cjwbw/aniportrait-audio2vid
OfficialView on Replicate →
Audio-Driven Synthesis of Photorealistic Portrait Animations
Capabilities
1:14:33:416:99:162:33:2Reference ImagesSeed
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
audio* | string(uri) | Input audio | — | — |
image* | string(uri) | Input image | — | — |
fps | integer | Frame per second in the output video | 30 | — |
guidance_scale | number | Scale for classifier-free guidance | 3.5 | — |
height | integer | Height of output video | 512 | — |
seed | integer | Random seed. Leave blank to randomize the seed | — | — |
steps | integer | Inference steps | 25 | — |
width | integer | Width of output video | 512 | — |
audiorequiredstringInput audio
imagerequiredstringInput image
fpsintegerFrame per second in the output video
Default:
30guidance_scalenumberScale for classifier-free guidance
Default:
3.5heightintegerHeight of output video
Default:
512seedintegerRandom seed. Leave blank to randomize the seed
stepsintegerInference steps
Default:
25widthintegerWidth of output video
Default:
512Version:
3f976d8f2308Updated: 7/25/202614.9K runs
cinemasetfree.com