Florian Vahl
Florian Vahl
Hi @vesper8 Thanks for the feedback and the infos. Also thanks for sharing the other project with us. There is indeed a user interaction needed for the second client. But...
> I think that other members of the Hamburg Bit-Bots use it for experiments, too. For example @Flova. Yeah, I used it so schedule many long-running experiments/ablations in these three...
Thank you! Zudem hallo nach Braunschweig :D I am currently a bit busy, so I am not able to dive too deep into the different implementations, but I noticed, that...
Did you try to train for more epochs? Is sounds kind of weird, but maybe the optimizer choice or something else is different to the training setup of the pretrained...
It is based on Googles Imagen (closed source) and does not require retraining of the 2D diffusion model. I think it could work with stable diffusion instead of Imagen. The...
I thought about doing one, but even tho I trained a few diffusion models and know how a NERF works (never implemented one), I am not confident enough to build...
I don't think they use the diffusion model as a discriminator in the normal sense (like e.g. in GET3D). They use it to slightly refine a random rendering of the...
I have the same problem with the 64bit Version. 32 bit would be also fine for me but it crashes while building saying it doesn't support x86.
I encountered this also in the past using yay, but forgot the workaround...
I only tested this using Ubuntu 20.04 I didn't use conda for the mentioned minimal example, just a venv. But I can test it using only `av`.