Make sure to change the weight (by default, it's :1 which is usually too high). I recommend you keep the weight around :0.5 to 0.9 for the best results. I found the best results at :0.9 and 0.8
What to Know
V2 is a merger between V1 and an unreleased iteration of the LoRA. The unreleased iteration was trained on Lykon's AnyLoRA - Checkpoint.
How to use LoRA
Make sure to change the weight (by default, it's
:1which is usually too high). I recommend you keep the weight around:0.5 to 0.9for the best results. I found the best results at:0.9 and 0.8What to Know
V2 is a merger between V1 and an unreleased iteration of the LoRA. The unreleased iteration was trained on Lykon's AnyLoRA - Checkpoint.
Where it also works
The LoRA has been tested on AOM2SFW, AnythingV5,