IronCatFateToon

I'm back! This is a reupload of my IronCatFateToon merge checkpoint I was still able to find. I should not have removed my resources on here and my account...

---

Making models is a thing I do for fun. So if you like what I do? You can help me out by just using the model and leaving a review!

IronCatFateToon's goal is to be able to create nice looking anime style images with vibrant colours, more simplistic anime (cartoony) colour/style look and with influence of Fate/Stay Night: Unlimited Blade Works styling. This checkpoint has the VAE kl-f8-anime2 baked in.

In order to achieve what's just been promised I used MeinaMix V8 as the base checkpoint, I then merged two of my style LoRA's into MeinaMix V8; Anime vibrancy & simplifier Style (Merge ratio of 0.4) & Fate/stay night: UBW Style (Merge ratio of 0.6). And finally I merged the result of that with the checkpoint Mistoon_Anime. Where I did a weighted merge, 70% was used from the results of me merging the LoRA's into MeinaMix V8. And 30% was used for Mistoon_Anime. (Note: I didn't use the exact same Anime vibrancy & simplifier Style LoRA when merging, I retrained on the same dataset from that LoRA for a more nuanced look that complimented MeinaMix V8 better i.m.o.)

Some things you might recognize from Fate/stay night: UBW in this checkpoint, is in the way how eyes, scenery, city, cityscape, sky, grass, trees, certain 2.5D angles et cetera are generated. The anime/cartoony look is a combination from my Anime vibrancy & simplifier Style LoRA and Mistoon_Anime. While MeinaMix V8 as a base gives in my own opinion a really sollid base for good looking art.

I haven't used any embeddings in the example images so you should get a good idea, in what the checkpoint can create on its own. I generated the images using some wildcard libraries, so the prompts might sometimes seem random.

Advice:

• I would recommended a clip skip of 2

• I personally use R-ESRGAN 4X+ Anime6B as an upscaler a lot

• I am personally a fan of using DPM++ SDE Karras with 15 steps and when Hires fixing, I like to use 10 for Hires steps and a denoise of about 0.35 or 0.4. Most example images use 512x768 as base resolution.

• If you want the same vibrant, high contrast style look from my images you've seen, mostly in the images with girls, I suggest the following starter prompt: (masterpiece, best quality:1.4), cinematic light, colorful, high contrast, the prompt cinematic light is optional but I've used it in most of the example images since I liked the look. The high contrast prompt may sometimes do bad in certain NSFW generations, if you notice it in a seed you can try to remove it.

  • The starter prompt is not necessarily needed, I also included 2 examples where I just typed out a story based prompt and only used the negative prompt like below. And those images also came out great i.m.o.

• I would advice the following starter negative prompt in general to get the look you see in most of my example images: (worst quality:1.2), (low quality:1.2), (lowres:1.1), (monochrome:1.1), (greyscale), multiple views, comic, sketch. You can also use my full negative prompt from my sample images, if you liked the look of them.

  • The bad-artist negative embedding seems to work pretty nice too, which you can try instead of my suggested negative prompt.

This model wouldn't have been possible without these awesome creators:

• @Meina for MeinaMix V8

• @Inzaniak for Mistoon_Anime

• hakurei for kl-f8-anime2