DarkAlchy
DarkAlchy
Well, shoot. Readme said 3000 but I tried that port and nothing was there so that explains it. The instructions for all of this is ver discombobulated at best.
def generate(self, image, sample=False, num_beams=3, max_length=30, min_length=10, top_p=0.9, repetition_penalty=1.0): image_embeds = self.visual_encoder(image) Do we have to adjust that instead of a front interface?
No matter what I tried it always stopped right there in mid sentence.
I have had it do it on some others as well. The problem is this is Blip instead of blip2 or llama which do this far less often.
Not working here and I updated a few hours ago. This may have something to do with it: ValueError: File cannot be fetched: D:/stable-diffusion-webui/extensions/stable-diffusion-webui-promptgen/javascript/promptgen.js. All files must contained within the...
oogabooga+Qwen-VL, how?
> \train_network.py", line 747, in train text_encoder.requires_grad_(False) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ AttributeError: 'list' object has no attribute 'requires_grad_' When training sdxl's lora Yep, same here. edit: I am working with this now and...
> @DarkAlchy, sorry, the solution wasn't entirely developed by me, I used an idea that was sent to bmaltais's repository, but with some adjustments because of the many updates that...
> > Thank you for opening this PR. I'm not sure `text_encoder.requires_grad_(False)` stops the training for Text Encoder. It may be needed to set `requires_grad_` for `network`. I will test...