Verified: 9 months ago
SafeTensor
Type | |
Stats | 1,361 11,155 |
Reviews | (200) |
Published | May 27, 2024 |
Base Model | |
Training | Epochs: 40 |
Usage Tips | Clip Skip: 1 Strength: 1 |
Hash | AutoV2 DA9BFD7961 |
Lora trained in re-create Asou's art style.
I rlly like see your reviews and generations. They are helpful for fix and train better models. Share some hearts at the previews that you like and feel free to leave your comments or requests, but I can't promise anything xd.
Version 2: LoKr
I re-trained it and just in 2:40 hrs, it outperfoms the LoRa version for a wide range. Aditionally, I pruned a little the dataset and I re-taged it just by the way. This one has a rlly hard NSFW attire.
Weight: .8 - 1
Version 1: LoRa
This was an experiment for check if was possible re-create the noise texture in a lora. I trained it around 7 hours but I don't know If I convinced, but it took the warm colors and other features (Like the blur of deep of field).
Trigger: asoustyle
Weight: .8 - 1