Krea2 Version
This is an experimental LoRA version trained on Krea2 Raw FP8.
No Trigger word for this version
Recommended strength is 1.0
Recommendation to Anima/Krea2 Lora Trainer I am working on /ᐠ ̷ ̷𝅒 ̷‸ ̷𝅒 ̷ ᐟ\ﾉ
https://github.com/WalkingMeatAxolotl/AnimaLoraStudio
------------------------------------------------------------------------------------------
Noob Version
Trained on NoobAI V-Prediction.
Trigger word
t4num4Recommended strength is 1.0 on WaiNoob
------------------------------------------------------------------------------------------
Anima Version
This is an experimental LoRA version trained on Anima Preview.
Anima is a new DiT model focused on anime concepts. You can find it on Hugging Face at circlestone-labs/Anima · Hugging Face
Trigger word
@4x0styleRecommended strength is 1.0
Recommendation to Anima Lora Trainer I am working on /ᐠ ̷ ̷𝅒 ̷‸ ̷𝅒 ̷ ᐟ\ﾉ
Description
Trained on Krea2 fp8 raw
FAQ
Comments (2)
🤔刚开始炼画风lora想问下，原图是2600x4000+类似的分辨率，一般来说怎么切图最后训练出来的结果会比较好，需要专门切几个1024x1024类似的不会压缩的小图吗？
大部分训练器都有 arb 筒，会自动拉缩到指定分辨率，裁剪是为了解决画面中元素所占得比列。比如如果想要更多的表现眼睛的画风，那把图片保证分辨率的情况下裁到只剩下上半身甚至脸，效果会比用全景图好很多。