Trained on 332 images with Natural Language and captioning that has been checked by hand and edited on 70% of the BLIP-2 Captions.

WD-14 tagging is a custom dictionary with manual appending.

1. Use negative -"Large Breasts" when using positive +"small breasts" or +flat chest

2. Use Natural Language with VIT tagging only where needed.

3. Tested with Anime and Realistic models - Use negative or neutral realistic for most uses

4. Pony Realism and like models will overbake without "realistic" in the negative prompt or at minimum not used as a positive prompt.

Thank you for continuing to support my training addiction with your tip (By default I know) of just 1 buzz per generation while using this lora.

An example of my cost:

1. 11¢ per hour for training power consumption

2. 15¢ per hour for amortization of equipment cost over 3 years

3. For this model a data set was shared with XL paid time around $500 per model