MeMaXL Flat Anime Style - Pony/XL/Illustrious Lora
v4.0 A [Zootlustrious-v2]
These loras were trained on images from Megami Magazine from late 2018 to early 2024. Please read the About This Version for more information. Please use the lora based on the model for the optimum results.
V3 Type B: Trained using 52 images selected for their similar eyes and hair. Trained on Hadrian DeliceXL 2.0 and AutismMix .
V3 Type A: Trained using 50 images selected for their similar eye style and detailed backgrounds. Trained on AutismMix, Hadrian DeliceXL 2.0, Ponymagine , Illustrious-XL v0.1.
V2: This lora was trained using 150+ images that I painstakingly removed the japanese text from. Trained on AutismMix.
V1: Trained using 1,200+ images. (All I had.) Trained on Based Pony.
To get the results you see in the images above, these are the settings I used.
Prompt(Pony): score_9,score_8_up,score_7_up,score_6_up,source_anime, <lora:MeMaXL:1> [your prompt]
Negatives(Pony): mosaic censoring,bar censor,censored,source_cartoon,source_pony,source_furry,simple background,
Prompt(XL): highres,absurdres,masterpiece,best quality,(anime screencap:0.5),
Negative(XL): worst quality,bad quality,lowres,jpeg artifacts,monochrome,bad anatomy,censored,multiple views,4koma,simple background,blurry background
Sample: DPM++ 2S a
Steps: 24-26 (Whatever gives you the best results)
CFG Scale: 5-7
Extension: [sd-webui-color-enhance] set to 0.5 (this increases the saturation a bit)
Upscaling: Follow this method
Popularity
Info
Version v4.0 A [Zootlustrious-v2]: 1 File
About this version: v4.0 A [Zootlustrious-v2]
Trained on 50 images from the Type A dataset. The base for this lora is Zootlustrious V2. I haven't tested it on any other model and I don't expect it to work as well if you're not using ZootV2.
The results of this lora is probably the most accurate I've achieved to the Megami Magazine style as of posting this lora. Even though the illustrious brand of models already have a Megami Magazine tag. The tag gives you an awful text in every gen, so this lora should be very helpful as an alternative.
To get similar results you see in the gallery images, just use this in the positive:
highres,absurdres,masterpiece,best quality,And this in the negative:
worst quality,bad quality,That's it. Anything more, especially in the negative, may result in a loss of style accuracy.
Yes, I know the size is bigger than my other loras, it was a result of the setting changes with my training. No, I don't plan to make a smaller version. Please use the appropriate model for each lora.
19 Versions
Go ahead and upload yours!
