DoBetter

Results 19 comments of DoBetter

Hello,are you fine-tune in already? I‘m also curious about how much vram and ram is needed?Thanks a lot.

Hello, have you succeeded yet? I am also working on this problem, could you share your thoughts?Thanks a lot

> I see the images in logs, but I don't understand what exactly is of the five picture below. > > train/conditioning train/inputs train/reconstruction train/samples train/samples_cfg_scale_3.00 > > Can you...

sorry to bother you,have you solved the problem yet?

Thank you for your quick reply,I see another #34 and the method is the same, and it works

> Hi @xdobetter Thanks very much for the issue! Looking at the traceback, it looks like the issue is on diffusers side: > > ```shell > File "J:\Research_Program\peft\examples\lora_dreambooth\train_dreambooth.py", line 1007,...

But the pre-train model is saved to the default cache location, should I give this path as well?

I have same problem, I step by step finish [PyTorch and Mitsuba interoperability](https://mitsuba.readthedocs.io/en/latest/src/inverse_rendering/pytorch_mitsuba_interoperability.html#) case,but I found save to .ipynb,there no problem,but save to .py the problem produce. why happen these...

Thank you for your quick reply again , made me less worried about it.