This is a very old model of mine and does not conform to my new very high-quality standard established with my "Essenz" model series, so please do not use this! It will be replaced in the near future with a new and better model in the "Essenz" series!

• Current version: v1.0

• Recommended weight: 0.8-1.0 (the more LoRa's are chained together the lower this needs to be)

• Recommended VAE: SDXL 0.9

• Recommended model: SDXL 1.0

• Recommended inference settings: See example images

I recommend using the official SDXL 1.0 model that has the SDXL 0.9 VAE already integrated, which you can find here.

Trigger words

• giant x

• miniature x

• giant x cramped inside a room

Further usage notes

Prompting just "giant woman" or "miniature woman" will not prompt the size. You need to tie it to an action/position like "giant woman standing in a city street" or "miniature woman standing on a forest ground next to a mushroom"!

This LoHa tends to generate naked women if you do not negative prompt "naked" and/or specifically mention clothing in the positive prompt.

This LoHa works best when using a render style in the positive prompt, while photos and digital art work less well.

This LoHa was generally trained on three distinct concepts: giant people in a city, giant people cramped inside rooms, and miniature people. It thus works best with those concepts and with people, but you may try other concepts and subjects, too.

Use "toy, figurine" in the negative prompt to prevent the subject from becoming an action figure when prompting miniature people.

Changelog

v1.0

• Initial release

Description

Giants and Shrinks Concept LoHa for SDXL 1.0 trained (not merged) by me (AI_Characters). Credit is not mandatory but I would still appreciate credit when posting images using this LoHa on social media! Feel free to @ my Twitter and/or Instagram accounts too (@ai_characters)! I would love to know when it is used!

If you want to support what I am doing, donations to my Ko-Fi would be greatly appreciated! Those will go towards funding the renting of GPUs for further experimentation and model making.

Feel free to also try out my RVC2 AI voice models which you can find here!

Stats

Dataset:

• 94 images (renders and artworks)

Training:

• rented RTX A4090 on Vast.ai

• Training time: ~1h

• Example training configuration (v3)