search

TencentARC / PhotoMaker

PhotoMaker [CVPR 2024]
https://photo-maker.github.io/
Other
9.58k stars 768 forks source link

99大佬，能增加采样器CFG等选项吗？想用加速模型~ #84

Open aimarxjg opened 10 months ago

aimarxjg commented 10 months ago

已经在COMFY里面成功使用，也蛮像的 20102032

但是8G卡特别慢（1070TI），默认50步出图我花4000秒........我想使用XL的TURBO或者LCM模型来加速，需要修改采样器调度器CFG等参数，谢谢拉~😉

Paper99 commented 10 months ago

OK, I'll investigate it.

Paper99 commented 10 months ago

An important note: For those GPUs that do not support bfloat16, please change this line to torch_dtype = torch.float16, the speed will be greatly improved (1min/img (before) vs. 14s/img (after) on V100). The minimum GPU memory requirement for PhotoMaker is 15G.

Paper99 commented 10 months ago

This is an alternative solution.

aimarxjg commented 10 months ago

谢谢您的指导~

Paper99 commented 10 months ago

Please refer to this URL: https://zenn.dev/neoai/articles/cedda3d17f0a70, for using LCM-LoRA with our PhotoMaker. This blog also provides many analyses. It is interesting.