Trained over 46 images for 1024 using NoobAI Epsilon-pred 1.1 as a training model

• Weight: 1 is perfect

• Tags: there aren't any trigger words or recommended tags so go wild

• You can use sd couple or regional prompter to make the lora even better but it isn't required

If you wanna support me or request a commission ko-fi

Additional information:

• Webui I use

• VAE: MS DPipe fp32 112k Anime VAE SDXL

• Sampler: Euler a | Scheduler: Align Your Steps

• Steps: 24 | Hires: 12

• Denoise: 0.4 | Upscale: 1.5

• CFG: 6

• ADetailer for faces