v3.0: Ground Zero is available for generation on tensor.art!
Grounded generates realistic images of realistic women. Not another merge of merges, Grounded is made from trained checkpoints, particularly ones that specialize in amateur photography, and, therefore, amateur women. It excels in believable faces, realistic breasts, and diverse body types.
All samples were generated without embeddings, loras, or upscaling.
Recommendations for v3.0:
Clip skip: 1
CFG: 4-8
20-40 steps
512-768
DPM++ SDE Karras
Avoid negative embeddings/complex negative prompts
Description
Used some add difference merges to basically strip out everything professional and glossy - everything that made it like Elevated. What I got, I think, is a distilled version of my original vision for the checkpoint. I’ve had so much fun with it that I actually decided to upload again. SD1.5 may be limited and old, but dammit, so is my hardware!
FAQ
Comments (2)
Number 3 wouldn't work for me the other day when I tried it. I wish it would as your grounded checkpoints are among my faves.
Hey! Thank you for the kind words. The first upload was bad for much of day one. A fix has been uploaded, so I would encourage you to try again!
My computer is not very capable, so I do everything in the Draw Things app on my phone. This can cause “size mismatch” issues that I don’t understand, but can fix with AI. This will be a preliminary check, going forward.