Hey! This is my first Mix so it might not be the best but i hope you give it a try!
I highly recommend to use this model with artist tags, styles tags, or at least stylistic LoRas as the base style is very neutral/simple.
I hope all of you have fun with your creations!!
I would love to know what you think of it. All feedback is welcome!
v5 is out!
No LoRAs were used on the showcased images, and half of them are not even upscaled/hires-fixed, so you can achieve high quality without using anything other than prompting.
Recommended Settings:
Sampling Method: DPM++ 2M and DPM++ 2M SDE for v5
Scheduler: SGM Uniform
CFG Scale: 4-5
Steps: 25
You dont need to use upscaler/hires/adetailer for portraits/closeups if you dont want to since this model perfoms the best at it. Some images on this post dont even use any of it.
ADITIONAL OBSERVATIONS:
This model can easily go from semi realistic to common anime style with a few words added to your prompt. Also this mix have GENESIS LoKr model built on it so you can achieve a even wider variety of styles(try adding more weight if you are not seeing much difference).
Here you can find more about GENESIS:
Recommended Negative prompt:
lowres, (bad quality,worst quality:1.2), worst detail, sketch, censor, transparent background, patreon logo, bad_anatomy, artist_name, twitter username, patreon username, signature, text
worst quality, bad quality, jpeg, artifacts, (bad hands, bad finger, anatomy), (artist name, copyright name, watermark, text, english text), (bad feet, bad toes), (bad quality,worst quality:1.2), worst detail, sketch, censor, transparent background, patreon logo, bad_anatomy, artist_name, twitter username, patreon username, signature, text, (copyright name:1.2),(watermark:1.2)