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
I can’t seem to stop fiddling with this. Went back to v1.1 and tweaked from there, and felt like I came to something a lot better than v1.2. Lots of small merges, experimented with add difference, strengthened some older models that had faded into the background.
I’m particularly proud of how the checkpoint handles breasts.
FAQ
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.