Download
1 variant available
fp16 SafeTensor
djzRetroTide_LB3.safetensors
Half precision, best balance • 104.64 MB
Verified: 3 years ago
870 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
(24)
Mar 19, 2023
SD 2.1 768
This experimental model has been overtrained to 20 epochs on 40 repeat, using network Dim 64 alpha 32. As with the DB2 models, the dataset is not captioned. Epoch 10 was selected after evaluation.
Show more

8950 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
2.8K0 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K
27.9K0 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9.0 1 2 3 4 5 6 7 8 9K

License:
CreativeML Open RAIL-MThis is djzRetroTide Lora Dreambooth
- loves to be stacked with other LORAs
v21-DB2 no captions, pure style model designed for Stacking.
v21 - trained on dataset sharing the same name, BLIP2 captions
(prompting captions produces close variation on ground truth)
Danger Helpers here:
https://civitai.com/models/20517/danger-zoo-johnsons-negative-embeddings-helper-collection

