Scribd
Upload
27 views

Fofrface-To-many - Run With An API On Replicate

The document summarizes a face-to-many AI service that can take a photo of a face and convert it into different art styles like 3D, pixel art, or video game characters. It provides inputs to customize the conversion including image, style, prompts, and adjustment settings. The output is a preview and download of the converted image. It also gives runtime costs and notes that it uses non-commercial weights requiring attribution and has additional resources like examples, readme, and information on the Loras used.

Uploaded by

ftjppwzdgk
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
27 views

Fofrface-To-many - Run With An API On Replicate

The document summarizes a face-to-many AI service that can take a photo of a face and convert it into different art styles like 3D, pixel art, or video game characters. It provides inputs to customize the conversion including image, style, prompts, and adjustment settings. The output is a preview and download of the converted image. It also gives runtime costs and notes that it uses non-commercial weights requiring attribution and has additional resources like examples, readme, and information on the Loras used.

Uploaded by

ftjppwzdgk
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

Menu

fofr /
face-to-many
Turn a face into 3D, emoji, pixel art, video
game, claymation or toy

Public 2.3M runs GitHub

License

Star

Run with an API

Playground API Examples

README Versions

Input
Form

image file

Drop a file or click to upload


IMG_1510.jpeg

Take a photo with your webcam

An image of a person to be converted

style string

Video game

Style to convert to
Default: "3D"

prompt string

cool,ps2,pretty

Default: "a person"

negative_prompt string

boring

Things you do not want in the image

denoising_strength number
(minimum: 0, maximum: 1)

0.65

How much of the original image to keep. 1 is the


complete destruction of the original image, 0 is
the original image
Default: 0.65

prompt_strength number
(minimum: 0, maximum: 20)

10.91

Strength of the prompt. This is the CFG scale,


higher numbers lead to stronger prompt, lower
numbers will keep more of a likeness to the
original.
Default: 4.5

control_depth_strength number
(minimum: 0, maximum: 1)

0.8

Strength of depth controlnet. The bigger this is,


the more controlnet affects the output.
Default: 0.8

instant_id_strength number
(minimum: 0, maximum: 1)

0.8

How strong the InstantID will be.


Default: 1

seed integer

Fix the random seed for reproducibility

custom_lora_url string

URL to a Replicate custom LoRA. Must be in the


format
https://replicate.delivery/pbxt/[id]/trained_model.tar
or
https://pbxt.replicate.delivery/[id]/trained_model.tar

lora_scale number
(minimum: 0, maximum: 1)

How strong the LoRA will be


Default: 1

Reset Run

Output
Preview JSON

Generated in 11.3 seconds

Tweak it Share

Download Report

Hide logs

82%|████████▏ | 14/17 [00:04<00:00, 3.44


88%|████████▊ | 15/17 [00:04<00:00, 3.45
94%|█████████▍| 16/17 [00:04<00:00, 3.47
100%|██████████| 17/17 [00:04<00:00, 3.49
100%|██████████| 17/17 [00:04<00:00, 3.45
Executing node 5, title: Save Image, class
Prompt executed in 9.43 seconds
outputs: {'4': {'images': []}, '5': {'ima
====================================
Contents of /tmp/outputs:
ComfyUI_00001_.png

Copy logs

Fullscreen logs

Download logs

View more examples


Examples

Run time and cost

This model costs approximately $0.0094 to


run on Replicate, but this varies depending
on your inputs. It is also open source and
you can run it on your own computer with
Docker.

To see how much you've spent, go to your


dashboard.

This model runs on Nvidia A40 (Large) GPU


hardware, which costs $0.000725 per
second. Predictions typically complete
within 13 seconds.

Readme

Non-commercial use only.

It uses the following weights which are


non-commercial: InsightFace antelopev2
(which is used by InstantID)

Follow me on Twitter @fofrAI

Loras

Many of the loras are made by


artificialguybr. If you like them you can
make a donation to their Patreon or Ko-fi:

https://www.patreon.com/user?
u=81570187

https://ko-fi.com/artificialguybr

Or follow them on Twitter:

https://twitter.com/artificialguybr

Replicate All services are online

About Guides Terms Privacy Status

GitHub X Discord Support

You might also like