Open SuSung-boy opened 9 months ago
yes
@guoqincode hello sir, that means after stage1 training, the unet cannot generate content based on the prompt word? if i set unet.requiresgrad(False) and unet.eval(), will unet still gain the ability to generate content based on pose while maintaining the ability to generate based on prompts?
@guoqincode hello sir, that means after stage1 training, the unet cannot generate content based on the prompt word? if i set unet.requiresgrad(False) and unet.eval(), will unet still gain the ability to generate content based on pose while maintaining the ability to generate based on prompts?
Why not give it a try?
@guoqincode hello sir, that means after stage1 training, the unet cannot generate content based on the prompt word? if i set unet.requiresgrad(False) and unet.eval(), will unet still gain the ability to generate content based on pose while maintaining the ability to generate based on prompts?
Why not give it a try?
thank you sir ,i will try. but i have very few GPU resources :( ... ,it will take a very long time. so if you can give me some advice ,It's a great help to me. tranks
where are pretrained weights?
I find different epoch checkpoint weights are different, does this mean the unet is trainable?