Just in time for Halloween, Monster Diffusion is back and is an enhanced version of the original Monster Diffusion model, now leveraging the power of Stable Diffusion SDXL to generate high-quality horror centric images. It's an all-in-one model replacing my old 1.5 models Monster Diffusion, Creepy Diffusion and Evil Clown.
This model is good for:
Gore, monsters, creatures and realism.
Happy prompting
Description
Monster Diffusion SDXL is an bring Monster Diffusion to the next era, now leveraging the power of SDXL to generate high-quality. This upgraded model not only recognizes a wide array of monster-related keywords but also incorporates a Noise Offset feature to create a unique, realistic look for the generated images.
This model is good model:
Gore, monsters, creatures and realism.
Enjoy
FAQ
Comments (6)
It's interesting that the 2.1 model looks a lot more "serious" and real than the XL version. Same dataset? Perhaps the training method isn't quite the right one, or the prompting could be refined. I'll play with it on my end.
So good and so SPOOKY!
This is truly some ugly sh*t, great job!
I love this horrific checkpoint! Thanks for creating these beautiful nightmares
Does the SDXL model have a baked VAE?
Are you able to create images with this in an anime style?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.