⭑ About this version:
˟ Lighting improvement
˟ Better style
˟ Closer to v2 and v3 style composition
⭑Added trained Lora:
˟ Cleaned style
˟ Baked in VAE
˟ Extra trained data of 15000 steps
˟ Better Lora support
⭑Suggested settings:
•I had CLIP skip 2 on every image
•I had ENSD: 31337 all of them
•All of them had highres.fix or img2img at higher resolution.
•I don't use restore faces
•I use afterdetailer for face details
•Tiled diffusion for img2img upscaling and sometimes Noise Inversion for some more extra details.
•4x-Ultrasharp upscaler
