Hongrui CHEN comments

Results 5 comments of


                                            Hongrui CHEN

Questions about the low benign accuracy on CIFAR-10 and GTSRB dataset of Blind Backdoor

> I think my config for cifar confused pre-trained models, but I think simply using a fixed scale and not MGDA will work better. hello, I am also try to...

Questions about the low benign accuracy on CIFAR-10 and GTSRB dataset of Blind Backdoor

> I guess you can just set it to 0.9 Thank you for your fast reply! Here you mean clean:backdoor = 1 : 0.9 or clean:backdoor = 0.1 : 0.9...

Have any guide for training flux Fill lora, or fine-turn flux Fill?

I saw this issue, and also want to understand difference between flux, flux fill and flux kontext model. So I dive into the code of diffusers. A short answer is...

How can I switch between LoRA models dynamically?

Hi, after I read through the lora code file. I think there are two ways to change lora without reload the whole base Flux model. 1. Use Lora as definition...

How can I switch between LoRA models dynamically?

I implement the method one by replacing https://github.com/kohya-ss/sd-scripts/blob/498705770109e0823a465fc6872c691136b3202a/flux_minimal_inference.py#L475-L576 to ```python original_apply_to = lora_flux.LoRAModule.apply_to def patched_apply_to(self): self.org_forward = self.org_module.forward self.org_module.forward = self.forward self.org_module_ref_for_patch = self.org_module del self.org_module def patched_remove(self): if hasattr(self,...