Thank you to these Creators with their models! This is a merge between these models:
RealCartoonXL - V7 - 7whitefire7
XXX-Ray - v1.0 - RaymondLuxuryYacht
Realstic Stock Photo - v2.0 - PromptSharingSamaritan
Juggernaut XL - Jugg_XI_by_RunDiffusion - KandooAI
Big Lust - v1.6 - waterdrinker
I have used these settings almost exclusively. They are a good starting point and can be adjusted depending on what you want to generate.
Recommended Settings:
Sampler: DPM++ 2M SDE
Res: 832*1216
Steps: 30-40
CFG: 3-7
Recommended Upscaler Settings:
Hires. fix Upscaler:
Hires steps: 15-20
Hires upscale: 1.1-1.5
Denoising strength: ~ 0.2-0.4
If you can use Hires.fix for better Results!
I don't use restore faces. If you got a bad face or want to change it use ADetailer for it!
I would greatly appreciate any feedback!
If you like this model, I would greatly appreciate a positive review along with constructive criticism, suggestions for improvement, or anything similar!
Description
FAQ
Comments (6)
Can you list which models/loras you merged into this? Thanks!
Sure I merged the following models:
FYI the baked in VAE in v1.0 of this model seems corrupt, it generates artifacts.
Using an external SDXL VAE works OK.
Thanks. Baked in vae is indeed broken it seems
Edit: If you don't mind, which checkpoint are in this merge?
I really like the style of this one :)
Sure I merged the following models: