https://civitai.com/models/63334 This lora not made by me, re upload from somewhere, because it is not provided here. This model is trained using base model as the previous version with way bigger dataset. There are two versions of it: EimisAnimeDiffusion_2-0 (original) (in there it is pruned) EimisAnimeDiffusion_2-0_alternative (original + orangemix:0.2 + even bigger dataset) (in there it is full) To download alternative version check files. Which model to choose EimisAnimeDiffusion_2-0 is trained on smaller dataset, however it keeps the style better. It might be worse on some aspects like hardly getting specific prompts or some other small issues, however it has way better quality, effects and keeps the style I wanted way better. EimisAnimeDiffusion_2-0_alternative on the other hand understands better way more prompts (especially in comparison with some NSFW prompts). However, way worse with style, effects, details. Also sometimes not as smooth, some stuff be random, but still really great alternative model.