
V2 is a merge of v1 and a Lora extracted from a dreambooth model. Might work better in some cases, worse in others. Not absolutely necessary if V1 is working for you.
This is a Lora of Canadian pop-punk singer Avril Lavigne. it was trained on the same 28 images as the embedding in my profile, though these were 768x768, whereas the embeddings training data was 512x512
描述:
28 images
trained in Kohya_ss
训练词语: loraavril
名称: loraavril.safetensors
大小 (KB): 147570
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success