这个模型使用了超过300张高质量的原始图片进行训练。
这个模型拥有很好的画风模仿效果。
一种1990年代的复古绘画风格。其特点是拥有又大又圆的眼睛。拥有类似传统赛璐璐风格的平涂色彩表现。
Flux版本：https://civarchive.com/models/745928
illustriousXL 版本：https://civarchive.com/models/1383933
Pony XL 版本：https://civarchive.com/models/361994
推荐权重：0.6~1.0
推荐模型：Animagine XL V3
--- --- --- --- --- --- --- ---
This model used more than 300 high-quality original pictures for training.
This model has a good effect of restoring the artist's style.
A 1990s retro painting style. It is characterized by large, round eyes. It has a flat color expression similar to traditional celluloid style.
Flux version：https://civarchive.com/models/745928
illustriousXL version：https://civarchive.com/models/1383933
Pony XL version：https://civarchive.com/models/361994
Recommendation Weight：0.6~1.0
Recommendation Model：Animagine XL V3
Description
FAQ
Comments (6)
相当好看！
Such a great Style Lora, thanks for sharing!
Have you thought about doing some of your style loras for Pony Diffusion V6?
I have trained many lora models using the Pony Diffusion V6 base model. It is undeniable that there is a probability of producing good pictures. However, the biggest disadvantage of Pony is that it mixes too many 3D and 2.5D materials, which will lead to the pure 2D style lora not being very good. Stably achieve the specified style
For example : https://civitai.com/models/344734
@flyx3 Interesting, I did noticed it does have a lot of 2.5D and 3D in it as you said. Someone released a more Anime focus version of PonyXL called AutismMix SDXL not sure if that model would be more suitable for your style loras. The loras seem to work well between PonyXL and AutismMix interchangeably, obviously with different results. Still thanks for the head up on your PonyXL loras, I didn't notice them. Hopefully you managed to find a way to make them work. Thanks for sharing the loras!
@darionk The lora model trained based on Pony XL can be used directly on the AutismMix SDXL base model, but the effect will be slightly different.