Only a performance update, no new characters or such. Improvements: - Better-formed eyes - Better hands - Fewer artifacts overall Worse: - Some tags, like "censored" in the negative, bring much darker or orange-tinted images - Backgrounds can look more blurry, noisy or messy, describing the background a bit more can change that - It makes sometimes strange dark orange like images Recommended negatives are "worst quality, bad quality, sketch". With negative "sketch" giving more clean line art (most of the time). Sometimes not using worst quality, bad quality, gives better results, strangely enough. Style A tends to produce better eyes with a more stable style overall, while Style 2.1 offers more detailed images with a less 2D appearance. If you prefer images with added detail and depth, Style 2.1 might be the better choice for you. Even if you need to kick the model in the balls sometimes. Note: Some concepts have a strong drawn appearence and others more of a 2.5 feel (especially with character prompts, giving more drawn results). The price of more versatility in general. Don't overload it with quality prompts or a wall of text prompts, its versatility is also its weakness. Overloading it with too much information can cause the model to produce unhinged results, because it don't have a strong "style saveguard". In maybe 2-3 weeks i have a dataset updated model, but it only offers new genshin characters so far.