POST
v1
/
replicate
/
videogeneration

Model

Query

model
string
default:
"anotherjesse/zeroscope-v2-xl"
required

The image model to be used;

Body

prompt
string
required

Input prompt

negative_prompt
string
default:
"blurred, noisy, washed out, distorted, broken"

Factor to scale image by

init_weight
float
default:
"0.5"

URL of the initial video (optional)

num_frames
int
default:
"24"

Number of frames for the output video

num_inferences_steps
int
default:
"50"

Number of denoising steps

width
int
default:
"1024"

Width of the output video

height
int
default:
"1024"

Height of the output video

guidance_scale
float
default:
"17.5"

Guidance scale

fps
int
default:
"10"

fps for the output video

video_model
string
default:
"xl"

Model to use

batch_size
int
default:
"1"

Batch size

remove_watermark
boolean
default:
"false"

Remove watermark