Models here will likely be builds using ideas I have for broad spectrum improvements to Flux using low to no compute, usually using methods I call "back-of-van ablation," and most focusing on improving generalization within the base model as opposed to focusing on particular concepts, running under the assumption that a lot of information is latent in the model and simply difficult to "access" due to a safety tuned unet.
描述:
This is a merge several loras and flux base. It needs a final fine tune but I am still collecting my dataset for that. Nevertheless, it works.
训练词语:
名称: yolkheadsFlux_yolkheadsTweakV05.safetensors
大小 (KB): 11622577
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
