prunaai / vace-14b

This is a faster VACE-14B model, optimised with pruna, contact us for more at pruna.ai

  • Public
  • 8.2K runs
  • Commercial use
  • GitHub
  • Weights
  • Paper
  • License
Iterate in playground

Input

*string
Shift + Return to add a new line

Prompt

file
Preview

Input video to edit.

file
Preview

Input mask video or image to edit.

file[]
https://replicate.delivery/pbxt/N323t5X69JB1MPD4w4cDIxK4rm0BG0W2JOWBrDrR4O9HTcyp/src_ref_image_1.png

Input reference images to edit.

string

Speed optimization level

Default: "Lightly Juiced 🍊 (more consistent)"

integer

Number of frames to generate.

Default: 81

string

Output resolution

Default: "832*480"

integer

Random seed (-1 for random)

Default: -1

integer

Sample shift

Default: 16

string

Sample solver

Default: "unipc"

integer

Sample steps

Default: 50

number

Sample guide scale

Default: 5

Output

Generated in

This output was created using a different version of the model, prunaai/vace-14b:bbafc615.

Run time and cost

This model costs approximately $0.76 to run on Replicate, or 1 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia H100 GPU hardware. Predictions typically complete within 9 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.