Help fuel my passion! Even $1 makes a difference.
让我保持创作热情,付费款/隐藏款模型可以在 爱发电 获取~
☕ https://www.ifdian.net/a/flyx3
-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- --
这个模型使用了超过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“retro artstyle 和 Old Version”可以获得漆原智志早期风格效果。
Flux 版本:https://civarchive.com/models/732879
Animagine XL V3版本:https://civarchive.com/models/269934
Pony XL版本:https://civarchive.com/models/347880
SD1.5版本:https://civarchive.com/models/49599
--- --- --- --- --- --- --- ---
This 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 "retro artstyle \ Old Version" to get early style effects for that artist.
Flux version:https://civarchive.com/models/732879
Animagine XL V3 version:https://civarchive.com/models/269934
Pony XL version:https://civarchive.com/models/347880
SD1.5 version:https://civarchive.com/models/49599
Description
FAQ
Comments (7)
这个又是什么版本……PDXL或者SDXL?
很明显,是illustrious XL版,新进潜力股~
@flyx3 搜了一下好像还没有明显优势,PONY之前在二次元的优势还是很明显,模型基数有优势。你觉得现阶段优势在哪?比如对提示词的兼容之类,我肉眼看不出什么优势
@Ryudo12345 测试了几千张,优点省流概括就是:色彩比pony好,稳定性比pony好,标签服从性比A3好,涩涩强于A3稍差于pony,底模自带支持的画师和角色更丰富。
缺点也非常明显:色块问题,部分细节表现很糟糕(例如:仔细看眼睛,虽然精致但是一团错乱)
@flyx3 你说眼睛错乱我还真没看出来……色彩看起来是比PONY稍微好一点,但也有限。最后说到涩图因为我是做涩图的果然PONY最好啊……
@Ryudo12345 pony最大的缺点就是不稳定(同样的素材训练lora,部分内容就是学不进去),导致的最终结果就是“只像同人图,不像原画”
Fantastic crisp results. Your retro anime LORAs are extremely high quality, you can tell how much work you put into training them to capture the artists' style. 10/10, thanks!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.



















