Last version before SDXL!
All example images were generated using only this model and no additional resources.
Model was trained using a corrected scheduler so dark scenes should be much easier.
Thank you to epiCRealism for the base of this model and all the model creators merged with it.
Description
Improved the dataset/captioning so should be easier to prompt as well as overall aesthetic/realism with a different merging technique after training.
This model was trained on Avalon TRUvision v2 and over 200 high quality hard/softcore images.
Edit: It's currently over-trained/over-fitted so creative prompts won't work as well, but merging this with more creative models should generate good results.
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.