ouhenio / stylegan3-clip

stylegan3 + clip

  • Public
  • 6.9K runs
  • T4
  • GitHub
Iterate in playground

Input

*string
Shift + Return to add a new line

Enter here a prompt to guide the image generation. You can enter more than one prompt separated with |, which will cause the guidance to focus on the different prompts at the same time, allowing to mix and play with the generation process.

string

choose model: FFHQ: human faces, MetFaces: human faces from works of art, AFHGv2: animal faces

Default: "FFHQ"

integer
(minimum: 1)

sampling steps, for FFHQ and MetFaces models, recommended to set <= 100 to avoid time out

Default: 200

string

choose output the final image or a video

Default: "mp4"

integer
(minimum: 1, maximum: 20)

choose video length, valid if output is mp4

Default: 10

integer

set -1 for random seed

Default: 2

number

learning rate

Default: 0.05

Output

This output was created using a different version of the model, ouhenio/stylegan3-clip:ef516e1e.

Run time and cost

This model costs approximately $0.10 to run on Replicate, or 10 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 T4 GPU hardware. Predictions typically complete within 8 minutes. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.