zengqixun12

Results 8 comments of zengqixun12

In mine mind, the ResBlock2-Resblock5 are the part of the stn network in order to figure out the θ.And the 'Affine network' in the paper,its work is to use the...

Thanks a lot for the answering!! In the stn network,the input and the output should be the same size,so I think the Resblock2-Resblock5 has the the same function as the...

> This two repos may help. First, you can convert controlnet into diffusers supported format, then just treat it as a regular SD model, and further add LoRA layers. @asadm...

> I have the same problem with you, is there any solution? I've solved this problem, and I combined Lora + Train + ControlNet + change basemodel, export the final...

> I have the same problem with you, is there any solution? I will release the code in few days ;)

> Not exactly, Lora is only effective on the main network and is independent from ControlNet

> commented thanks a lot, its quite uesful but its rely on Diffusers.So I still want to ask if there is any version with the traditional SD/control version rather than...