Note:
New versions v1.2, v1.2 SCALED, and v1.1 REALISM are now available on this model page! Version 1.2, v1.2 SCALED, and v1.1 REALISM are the same models as on the prior model page despite the file names being slightly different. This means that if you paid to download v1.2 or v1.1 from this model page, you do not need to pay for the v1.2 or v1.1 on this model page! They are the same models!
v1.2 and v1.1 are my new Tensor Art exclusive bipolar sliders LoRA for Illustrious XL 2.0. They are meant to affect the subject's age. These LoRAs come in two versions:
Version 1.2 is my classic all-around slider now better than ever. Currently, version 1.2 is primarily trained for female subjects.
Version 1.1 REALISM is built for realism. It's trained so that aging characters down does not give them overly large eyes, which is what what makes this slider LoRA so great for more realistic generations/
These Tensor Art exclusive versions builds off of my previous IllustriousXL Age Sliders by including more robust disentanglement. The previous age slider has an issue where it largely functioned as a glorified "MILF Slider". This meant that it was not as flexible. I am happy to say this has been resolved in these new and improved versions. This version also does not struggle with the male facial hair issues the prior one did.
~ How to use? ~
(Updated for v1.2, v1.2 SCALED, and v1.1 REALISM):
If you're using this LoRA with Tensor's Online Image Generation, use the SCALED version for full age range representation in +/- 2 weight.
This is a bipolar slider LoRA. That means it supports both positive and negative input weights.
For version 1.2, safe weighting is -5 to 5. No activation tag required.
For version 1.2 SCALED, safe weighting is -2 to 2. No activation tag required.
For Version 1.1 REALISM, safe weighting is roughly +/- 2. No activation tag required.
This LoRA is not trained for V-Pred models.
If you are using this LoRA in combination with a character LoRA, adding supporting tags can be beneficial to affect age. Since character LoRAs often have a set character age trained, it can be difficult to change that age depending on how intensely the character LoRA wants to maintain the character's "correct" age. To help overcome this, I suggest you use tags like aged up, aged down, petite , mature female, etc... as needed to help change the character's age. If you run into issues with using this LoRA, please feel free to send me a message or leave a comment so that I can fix issues that may arise.
If you run into issues with using this LoRA, please feel free to send me a message on CivitAI, or leave a comment so that I can fix issues that may arise.
~ Known issues for v1.2~
High positive weights (>= 5 for v1.2 and >= 2 for v1.2 SCALED) can influence breast size more than intended, as well as influence image contrast.
Version 1.2 is not very compatible with male subjects