FF Safe AnimXL (Lora, Lycoris +dataset)

่ฉณ็ดฐ

ใƒ•ใ‚กใ‚คใƒซใ‚’ใƒ€ใ‚ฆใƒณใƒญใƒผใƒ‰ (1)

ใƒขใƒ‡ใƒซ่ชฌๆ˜Ž

๐ŸŒŸ Trained specifically for style mixing on Safe For Work (SFW) dataset.

๐Ÿ”น Text Encoder (strongly reliant on U-Net architecture):

๐Ÿ”น Lora Model:

  • Trained using the CivitAI trainer.

  • Underwent training for 16 epochs.

  • Performance: Lora showcases stable diffusion in XL settings.

๐Ÿ”น Lycoris Models:

  • Configured using this preset from LyCORIS, but with our custom tweaks.

  • Trained on 8xA6000 GPUs.

  • Underwent 20-40 epochs with a batch size of 20.

  • Module Type Breakdown:

    • LohaModule: 176

    • LoConModule: 150

    • FullModule: 26

    • LokrModule: 700

๐Ÿ† Comparison:

  • CivitAI's Lora stands out in our tests, but we've yet to explore its full potential in style mixing with other models.

Feedback, collaboration, and tests are welcome! ๐ŸคŸ ๐Ÿฅƒ

ใ“ใฎใƒขใƒ‡ใƒซใง็”Ÿๆˆใ•ใ‚ŒใŸ็”ปๅƒ