The first of a series of art-style LoRA's for Flux.1-Dev. The approach is based on mnemic's experiments with not using a caption at all. It seems to work very well for simple art styles, where the effect is applied to the entire image, rather than just a portion.
Further experimentation with single-image training underway.
描述:
训练词语: sketch
名称: 814621_training_data.zip
大小 (KB): 28823
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: sketch.safetensors
大小 (KB): 18805
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
原文链接：https://1111down.com/1111790.html，转载请注明出处
