Version 2 - What's New
Improved anatomy and muscle structure
Variety of body types: From slim to curvy body shapes
Natural coloring and balanced contrast
Wide age range
Enhanced backgrounds with better perspective and depth
More natural face and body contours, reduced artificial look with improved skin texture
Various styles: Analog, amateur, professional, and more
Strengthened ethnic diversity
Wide range NSFW capabilities
Better prompt understanding and a broader range of poses
Better facial expressions
Recommended Generation Parameters:
Sampling method: LCM / Exponential
Sampling steps: 8-12
Resolution: 896x1152 / 832x1216 / 1344x768 and landscape
CFG: 1There is no need to add DMD LORA separately to the model; just load the checkpoint and run it!
I would appreciate your Buzz donations. I am developing this model solely with the Buzz points I’ve earned through the site
Warning!
This model is intended for ethical and responsible use only. Any attempt to use the model to create harmful, illegal, or unethical content will result in immediate disqualification and may lead to legal consequences. By using this model, you agree to comply with all relevant laws and ethical standards. Please use responsibly.
Description
Version 2 - What's New
Improved anatomy and muscle structure
Variety of body types: From slim to curvy body shapes
Natural coloring and balanced contrast
Wide age range
Enhanced backgrounds with better perspective and depth
More natural face and body contours, reduced artificial look with improved skin texture
Various styles: Analog, amateur, professional, and more
Strengthened ethnic diversity
Wide range NSFW capabilities
Better prompt understanding and a broader range of poses
Better facial expressions
Recommended Generation Parameters:
Sampling method: LCM / Exponential
Sampling steps: 8-12
Resolution: 896x1152 / 832x1216 / 1344x768 and landscape
CFG: 1There is no need to add DMD LORA separately to the model; just load the checkpoint and run it!
I would appreciate your Buzz donations. I am developing this model solely with the Buzz points I’ve earned through the site
Warning!
This model is intended for ethical and responsible use only. Any attempt to use the model to create harmful, illegal, or unethical content will result in immediate disqualification and may lead to legal consequences. By using this model, you agree to comply with all relevant laws and ethical standards. Please use responsibly.
FAQ
Comments (6)
v2.0 Tested on Krita AI, it has the same issue as "Into Realism DMD2 3.5" wich makes it unfit for me : it can't work with Controlnet depth (produces black images). Controlnet compatibility is very important (as much if more than loras) to have a versatile model...
Works perfect for me offline with comfyui. It follows very well the prompt! Sometimes I add some loras for special effekts. It is not easy to get als the feeds in the pic. Most time seems it was trained on cowboy shot pics :D
great work on v2.0, awesome!!!
this is the only checkpoint i've tried that takes SIX seconds to generate an image on my AMD gpu, compared to the 80 seconds it takes to generate a Z image turbo image. And this makes much better porn than zimg without the need for loras. Idk what kind of black magic is happening with it but it's incredible stuff.
What in the witchcraft is this??? This is the best checkpoint I have ever used! Its so freaking fast and consistent even on my 4GB VRAM card. Thanks for this amazing checkpoint.
When are we going to have an update?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.