XL_V2.0模型使用了超过1000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，训练图片全部来自该画师的原画集。
使用提示词“Old Version”可以获得漆原智志早期风格效果。
不添加额外提示词，可以获得漆原智志中后期风格效果。
Flux 版本：https://civarchive.com/models/732879
illustriousXL 版本：https://civarchive.com/models/885911
Pony XL版本：https://civarchive.com/models/347880
SD1.5版本：https://civarchive.com/models/49599
推荐权重：0.6~1.0
推荐CFG：4~5
推荐模型：Animagine XL V3
--- --- --- --- --- --- --- ---
XL_V2.0 version used more than 1000 high-quality original pictures for training.
This model has a good effect of restoring the artist's style.The training pictures are all from the original painting collection of the artist.
Use the prompt word "Old Version" to get early style effects for that artist.
Without adding additional prompt words, to get recent style effects for that artist.
Flux ：https://civarchive.com/models/732879
Pony XL：https://civarchive.com/models/347880
illustriousXL version：https://civarchive.com/models/885911
SD1.5：https://civarchive.com/models/49599
Recommendation Weight：0.6~1.0
Recommendation Weight：4~5
Recommendation Model：Animagine XL V3
Description
FAQ
Comments (8)
肉眼可见的质量提升！想问下有训练xl的text-encoder么还是只训练unet？
When using SDXL LORA model with LoRA, △ mark will appear.
Attaches. Several files are compatible with LoRA
Since it says that it has not been updated, I think there is no other option but to upgrade.
LoRAを使わせて頂きます。
Glad to see you starting to make SDXL loras too