Home
Creators
Search Recent Missing Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register Favorites Keys Review DMs Logout
Community
Telegram ThePornDude
Home Creators Posts Import Register Favorites Logout

Slider-LORA : Head size (Patreon)

Published:
2026-03-31 08:40:00
Edited:
2026-08-20 02:46:48
Imported:
2026-10
Tags:

Content

Supporters Only is not open to the public and cannot be accessed through any channels. It is an exclusive model available only to supporters. This is to express gratitude for your continuous support, which enables me to keep creating new resource packs. Thank you sincerely, and I hope you enjoy this carefully prepared little gift. Wish you a pleasant experience!

Checkpoint : Flux.2-Klein-9B

Type : Slider-LORA ( level-3 Exclusive )

Weight : ±6

Exclusive workflow : 👈

Function: Control the head size by adjusting weights.

For those who haven't used Slider-LORA, here's a simple guide prepared for you

Example :

-MGAsYcmFJL6j7vGpPftEQJhpzepZPjY7gX0imwuHq4

OK! That's all. I hope you'll like it.

🫡 May the AI-power be with you, see you soon !🫡

Disclaimer: My model or workflow is solely for learning and communication purposes and shall not be used for any commercial activities. All responsibilities for the generated content, including its legality, ethical implications, or potential misuse, are borne entirely by the user. By using this model or workflow, you agree to this principle. Please use it responsibly within the scope of local laws.

Files

Comments

Seth Leloup

Blessed. Hopefully it works well with edit, some of the loras have very weak effect in edit.

Whistler

They all work for I2I. I have tried and all worked! A Slider lora is basically a prompt helper so T2I is easier as you are building something from 100% noise so you are changing everything and a slider lora have a easier job in helping you. But for I2I you need to guide the AI more so it understand what you want to change. They would all work if you just wrote "replace the character from the image with another one." But then it will not look like the same person. So you must first find a prompt that actually change what you want it to, and some things can be really hard to figure out. So you can try turning off the lora and then take your time to figure out a good prompt that change the things you want, even a smaller change can sometimes be enough. Then you can add the slider lora to increase that effect. The same prompt is not guarantee to work on all images either so you might need to adjust it some depending on you original image. Another thing you could try is using the Flux2Klein-Enhancer nodes. They help with prompts and how much you want to preserve of the original image, I did not use that so it is not needed and not easy to find good values, but if you like to fiddle with things I think it can be good.