IF LoRA
A general style LoRA, the main goal is to improve the realism and look of model output. The sytle is focused on modern social media and influencer aesthetics, but is not limited to that. The training data was hand picked to enhance the aesthetic quality.
Trigger word: if
Training info: Trained with AIToolkit using batch size 9, which means that the(effective steps are higher than the raw numbers. This is just how AIToolkit does it.
I could not decide which version is best, so I publish these 3_
• 3000 steps
• 6000 steps
• 9000 steps
Recommended weight: 0.9–2.0 The 3000 steps version may benefit from stronger weights (closer to 1.5–2.0), though results can vary.
![[K2] IF-KREA by user_z on Tensor.Art](https://image.tensorartassets.com/cdn-cgi/image/anim=true,plain=false,w=500,q=85/model_showcase/0/5fadbd33-68b2-99d9-b956-60d35c7d30cb.png)
![[K2] IF-KREA by user_z on Tensor.Art](https://image.tensorartassets.com/cdn-cgi/image/anim=true,plain=false,w=500,q=85/model_showcase/0/dd9aee30-f15a-b94d-8785-5beded8fbc0e.jpg)
![[K2] IF-KREA by user_z on Tensor.Art](https://image.tensorartassets.com/cdn-cgi/image/anim=true,plain=false,w=500,q=85/model_showcase/0/302e55bb-8d02-9ca3-52ff-a10e64a25cc7.jpg)
![[K2] IF-KREA by user_z on Tensor.Art](https://image.tensorartassets.com/cdn-cgi/image/anim=true,plain=false,w=500,q=85/model_showcase/0/1f1b9077-2e22-f3f5-4413-2199443f37a3.jpg)