AI Generated Images Are Getting Too Real

LoRA, Model Mixing, and more text to image magic. Now you can generate 5 fingers easily, extreme photorealistic people and illustrations that you would think it’s taken from Pixiv.

LoRA: Low-Rank Adaptation of Large Language Models
[Paper] https://arxiv.org/abs/2106.09685
[Language Model Code] https://github.com/microsoft/LoRA
[Stable Diffusion Code] https://github.com/cloneofsimo/lora

Koiboi’s Video
[LoRA vs DB vs TI vs HN] https://youtu.be/dVjMiJsuR5o

I will not be able to link any model because they are all heavily NSFW. If you want to learn more about the model mixing details, you can join my Discord and it’ll be posted there! https://discord.gg/NhJZGtH

Special thanks to ButterCream, GenkiKun, koiboi, Niaka

This video is supported by the kind Patrons & YouTube Members:
🙏Andrew Lescelius, Chris LeDoux, Alex Maurice, Panther Modern, Jake Disco, Demilson Quintao, Tony Jimenez, Shuhong Chen, Hongbo Men, happi nyuu nyaa, Carol Lo, Mose Sakashita, Miguel, Bandera, Gennaro Schiano, gunwoo, Ravid Freedman, Mert Seftali, Mrityunjay, Richárd Nagyfi, Timo Steiner, Henrik G Sundt, projectAnthony

[Discord] https://discord.gg/NhJZGtH
[Twitter] https://twitter.com/bycloudai
[Patreon] https://www.patreon.com/bycloud
[PayPal] https://paypal.me/bycloudai

[Music] Slipstream
[Profile & Banner Art] https://twitter.com/pygm7