Realistic LoRAs

LORA
Original


Updated:

7.6K

Version Detail

SDXL 1.0
20
10
Triggering word is kwon-woman_nr1. The checkpoint is Juggernaut XL - Version 5. (Other checkpoints didn't produce her faces very well. But they still look very beautiful lol.) 0.8~1.0 setting works well for the LoRA. VAE: can be automatic, None or vae-ft-mse-840000-ema-pruned.ckpt 1024 x 1024 images tested. Sampling method: Euler a. sampling steps 25, cfg 6~7 Adetailer denoising strength: 0.25~0.3 Upscaling: do it as post-processing if needed. Thanks. Enjoy~ Any advice is appreciated!

Project Permissions

    Use Permissions

  • Use in TENSOR Online

  • As a online training base model on TENSOR

  • Use without crediting me

  • Share merges of this model

  • Use different permissions on merges

    Commercial Use

  • Sell generated contents

  • Use on generation services

  • Sell this model or merges

Comments

Related Posts

Describe the image you want to generate, then press Enter to send.