Animegao kigurumi for FLUX.1 dev
Trained with stock FLUX.1 dev
If the model load is not fp16 (fp8, nf4, Q4_0, etc.), increase the LoRA weight.
webui forge Q4_0 requires a LoRA weight of 3.5 or higher.
webui forge Q5_0 requires a LoRA weight of 2.4 or higher.
webui forge fp8(float8-e4m3fn) requires a LoRA weight of 1.65 or higher.
描述:
512, 512 resolution LoRA training version.
训练词语:
名称: flux-lora-agkr-512-2.safetensors
大小 (KB): 37514
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/1090904.html，转载请注明出处
