LoRA trained on Ahri

Anime models arent that good yet on sdxl but some 2.5D/3D checkpoints are really really good

models: Crystal Clear XL - CCXL, WyvernMix (1.5 & XL) - XL v1.1, 国风4 GuoFeng4 XL - V1.0-Real-Beta

comfyui workflow is embedded in the pictures

this embedding helps with hands: unaestheticXL | Negative TI - v1.3

ComfyUI custom notes that were used:

comfyui impact pack

SDXL Base Model, Refiner and VAE

Recommended settings:

• Make sure you are aware on the usage instructions of LORA

• VAE: sdxl_vae.safetensors · stabilityai/sdxl-vae at main (huggingface.co)

• Sampler: DPM++ SDE Karras or DPM++ 2M Karras

• Steps: 20 to 35

• Clipskip: 1

• Upscaler : 4x-UltraSharp(for 2,5D & realistic), 4xAnimesharp(for anime)

• CFG Scale : 5 to 9 (mostly 7)

• LORA weight for txt2img: 0.5-1 (for the examples i mostly used 0.8 and 1)

• Denoise strength upscaling: 0.3 to 0.55

For full body shots i recommend using: ComfyUI Impact Pack

or the a1111 alternative GitHub - Bing-su/adetailer