KaliMichi's AniToon - AnimeXL!

Finally! the new version of my AniToon style LoRA is here! This update is specifically designed to achieve a more anime-focused aesthetic, Trained to preserve the style's signature look while leaning heavily into a digital anime aesthetic—characterized by clean line art, vibrant colors, and high-contrast atmospheric lighting. It excels at capturing the polished finish of modern digital illustration, featuring soft gradients combined with sharp, defined edges without losing the characteristic AniToon Style.

Highly compatible with Anime-based and Comic/Cartoon-based checkpoints.

Note: The style and level of detail will be refined in later versions to truly capture that unique style. Additionally, the final results may vary depending on the base checkpoint you use.

Recommended Settings:

• LoRA Weight: 1 (Weights lower than 0.9 can lead to suboptimal results for the style.)

• Sampler: Euler a

• Steps: 30-40

• CFG Scale: 3-5

Pro Tip: you can achieve a more unique style by forcing the weights between 1 and 2, this will force a more unique style, the drawback is that the images will generate with more saturated colors and stiff poses or some artifacts, to solve that you can aply this on InPaint with a denoising between 3 and 4 after generating normaly with lower weights or by mixing it with another LoRAs

Note: Because of the training data, please make sure to specify the character's clothing in detail to avoid accidentally generating inappropriate content.