Verified: 8 months ago
SafeTensor
Type | |
Stats | 399 367 89 |
Reviews | (60) |
Published | Sep 19, 2024 |
Base Model | |
Training | Steps: 1,770 Epochs: 10 |
Usage Tips | Clip Skip: 2 Strength: 1 |
Hash | AutoV2 1C2B6EB6C1 |
Create pixel-art works, similar to the lightweight pixel art style of independent games, not PlayBoy style.
Instructions
As a stylized model, it does not require activation words and can be used with any character lora.
Derived Checkpoint
Generally speaking, I will only train checkpoint with the same parameters and the same dataset if lora training is successful.
The advantage of checkpoint is that the character's memory ability is stronger.
The advantage of lora is that the training cost is much lower than the model, so it can be updated at a higher frequency.