Verified: 2 years ago
SafeTensor
Type | |
Stats | 510 312 |
Reviews | (59) |
Published | Jun 15, 2023 |
Base Model | |
Training | Steps: 5,760 Epochs: 10 |
Trigger Words | b0b |
Hash | AutoV2 B60A1D2780 |
If you like my contributions to the community, please consider Buying Me A Coffee or check out my other sites on AllMyLinks
TRAINING INFO
Trained on 32 images
Trained at 1024 resolution
RECOMMENDED SETTINGS
TXT2IMG - A weight of 1 works just fine and will yield some interesting results, but I recommend a weight of 0.4-0.7 for more flexibility while still keeping Bob's style.
PROMPTS - I highly recommend using prompts that describe the landscape you want. Simply adding the lora to your prompts won't yield optimal results. For a full list of the prompts/captions used for training, check the Lora file's metadata in your webgui.