This model is a mix of mainly popular anime models.
KenythingV5 is the last version of this model. From now on I'm going to work on a new one.
Also you can check out AIBooru, a website on which you can share your AI-generated works with others.
======================================
Best VAE: vae-ft-mse-840000-ema-pruned or kl-f8-anime2 (highres fix or sd upscaling is desirable to use)
Best upscaler: 4x-UltraSharp
Textual Inversions I recommend to use: EasyNegativeV2 and EasyNegative | bad-artist | ng_deepnegative_v1_75t | bad-hands-5
======================================
Settings I prefer to use:
Sampler: DPM++ 2M Karras | DPM++ SDE Karras | Euler a
Steps: 20-25
Hires fix: 0 steps, upscale by 2, 4x-UltraSharp upscaler, denoise 0,5
VAE: kl-f8-anime2
Description
Extremely experimental model.
It was a attempt to make a dark style LoRA. Not what I wanted, but the style isn't that bad so why not to post it, right? That's why I injected the LoRA into Kenything-v5 :d