An experimental build of making 3.5 Large models and giving weights to each block layer ranging from 0.1 to 1.5 then averaging them out and merging with the custom 3.5 models applying SLG of 7,8,9

WF with SD1.5 upscale

WF with SD1.5 upscale with Detail Daemon

More Compares

Downloads last month
46
GGUF
Model size
8.15B params
Architecture
sd3

8-bit

16-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Model tree for ND911/SD3.5-Large-SLG-Weighted-Merge

Quantized
(8)
this model