Verified: 9 months ago
SafeTensor
Type | |
Stats | 345 9,079 2.7k |
Reviews | (40) |
Published | Jul 27, 2024 |
Base Model | |
Training | Steps: 1,600 Epochs: 4 |
Usage Tips | Clip Skip: 1 Strength: 0.7 |
Trigger Words | secluded beach wide portrait nature rocks |
Hash | AutoV2 8F0531D6B8 |
Experimental Pony training using Full FP8 and Adapt Lion.
In my testing 0.75-0.85 is the best lora value to use.
The Data Set was only landscape photos so the Lora is SFW possible.
Trained against this model - Works with some realistic models and not others.