Trained entirely on screencaps
Works with other lora
Recommended weight = 0.8 - 1
The Showcase images use weight 1
I built a fast and easy to use website for you!
Use my website to generate prompts of all the outfits, including a mix and match option with every other character I've uploaded!
Any kind of feedback on my models is highly appreciated!
I love seeing the images made with my models, dont be shy, post some!
Commission a character on my website or on Fiverr!!!
Description
Comments (4)
Contains only season one screencaps?
@HugMeIntoFace yes I havent been able to work on Season2 yet. It is on my to-do list though
Did krea2 know booru tags? What's the thing to consider using it other than anima tho. I'm having a confusion to use krea2 because anima is already that perfect, and krea2 heavily needs nfsw support
@Zammfushiguro not really, I am using the krea2 text enhancer to make tags work - I just don't feel like rewriting my 400 prompts. The tags of trained loras isnt a problem at all, but poses/background/action should be described with natural language only, if you're not using the text enhancer.
Krea2 can naturally generate 2K images, which kinda removes the need for any upscaler- but I agree that the negative points of Krea2 outweigh the positives. Krea2 has a higher resource requirement, the nsfw block is very annoying (although there are a ton of checkpoints that don't have that issue at all) and the available resources for Krea2 are pretty slim, because training Krea2 LoRAs takes absolute ages.
I personally like to use anima in my free time too. I would generally say Krea2 is good for professional use, while Anima is better for the average user