
This is my first LoRA on this site. I have many plans for improvement and am currently supplementing the dataset with images of many other characters from the DnD universe. Please let me know what is missing in this LoRA and what issues you encounter.
At the moment, it works best with portraits, animals, and nature.
It is recommended to blend this LoRA at a 0.2 ratio.
Trained words:
• wc1dnd_style
• digital painting
Best usage - FLUX Guidance 3.5
Use the first word for a DnD accent, and the second only for style when fewer DnD universe details are needed.
Training details:
• 1050 steps
• Batch size of 4 with gradient accumulation of 4
• 130 images
• 1024 px
描述:
First version
训练词语: wc1dnd_style,digital painting
名称: Flux.Digital_Painting_DnD.safetensors
大小 (KB): 74891
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success