You're looking at a specific version of this model. Jump to the model overview.

fofr /lcm-video2video:8ebd1cc4

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
prompt
string
Self-portrait oil painting, a beautiful cyborg with golden hair, 8k
Prompt for video2video
video
string
Video to split into frames
fps
integer
8

Min: 1

Number of images per second of video, when not exporting all frames
extract_all_frames
boolean
False
Get every frame of the video. Ignores fps. Slow for large videos.
max_width
integer
512

Min: 1

Maximum width of the video. Maintains aspect ratio.
prompt_strength
number
0.2

Max: 1

1.0 corresponds to full destruction of information in video frame
num_inference_steps
integer
4

Min: 1

Max: 50

Number of denoising steps per frame. Recommend 1 to 8 steps.
use_canny_control_net
boolean
True
Use canny edge detection to guide animation
controlnet_conditioning_scale
number
2

Min: 0.1

Max: 4

Controlnet conditioning scale
control_guidance_start
number
0

Max: 1

Controlnet start
control_guidance_end
number
1

Max: 1

Controlnet end
canny_low_threshold
number
100

Min: 1

Max: 255

Canny low threshold
canny_high_threshold
number
200

Min: 1

Max: 255

Canny high threshold
guidance_scale
number
8

Min: 1

Max: 20

Scale for classifier-free guidance
seed
integer
Random seed. Leave blank to randomize the seed
return_frames
boolean
False
Return a tar file with all the frames alongside the video

Output schema

The shape of the response you’ll get when you run this model with an API.

Schema
{'items': {'format': 'uri', 'type': 'string'},
 'title': 'Output',
 'type': 'array'}