A SDXL LoRA designed to achieve a unique style that mixes the detailed and high-quality rendering of Anime illustrations with a Western Cartoon-Comic aesthetic.
Highly compatible with Anime-based and Comic/Cartoon-based checkpoints.
KaliMichi's AniToon v1.5:
Enhanced hand, foot, and facial generation, alongside background and lighting refinements.
This update addresses style-specific rendering flaws from version 1.0. I employed a focused fine-tuning approach on hands, feet, and faces to yield highly consistent results.
Note: This is my first LoRA, so 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
Notice: Because of the training data, please make sure to specify the character's clothing in detail to avoid accidentally generating inappropriate content.
