MeMaXL Flat Anime Style – Pony Lora

This lora was trained on 1,200+ images from Megami Magazine from late 2018 to early 2024. The base for this lora is Pony Diffusion V6 XL so you will need that model to use this.

To get the results you see in the images above, these are the settings I used.

Prompt(at the start): score_9, source_anime, official art, [your prompt] <lora:MeMaXL-000002:0.87> (using ‘1’ seems to give worse results)

Negatives: 3D, CGI, render, photo, text, watermark, low-quality, signature, moiré pattern, downsampling, aliasing, distorted, blurry, glossy, blur, jpeg artifacts, compression artifacts, poorly drawn, low-resolution, bad, distortion, twisted, excessive, exaggerated pose, exaggerated limbs, grainy, symmetrical, duplicate, error, pattern, beginner, pixelated, fake, hyper, glitch, overexposed, high-contrast, bad-contrast,

Euler a

Steps: 35

CFG Scale: 7

Highres Fix: 4x-UltraSharp

These are just the settings I’ve tested so far, you might find something more effective. Yes, I’m aware of the text in every image. This is the result of the dataset used. I might go back and manual remove the text and retrain the data. Maybe….