Michael Powers

Possible to run on a 1080 with 8GB? (memory error)

1

I have a DELL XPS with an nVidia 1080 w 8GB. My hope was to run StyleGAN on this rather than needing to jump to the cloud. Possible? I disable...

deprecated function call in generate_samples

1

I am a bit lame with GitHub pull requests so here is a note that a call is deprecated: generate_samples.py:126: DeprecationWarning: `imsave` is deprecated! `imsave` is deprecated in SciPy 1.0.0,...

USE_SAGEMAKER is checked at the beginning of train.py but not in the arg code which includes a few sagemaker variables. Easy enough to comment out but would be nice just...

I was able to start with FirebaseRTC and create [twisty.io](https://twisty.io). This is a free service for creating short links to video chat rooms. No login or accounts required. The rooms...

The code base does not support resuming training … and it doesn't save the model state in such a way that one could resume. The code saves the state_dict data...

pytorch on windows does not support multiprocessing

6

I'm attempting to figure out which bits of the code attempt to spawn new processes since this fails on Windows 10 pytorch. I had to modify pcgan in a similar...

[INFORMATION REQUEST] Action words that v3 motion module can effectively respond to?

5

Does anyone have a list of motion training tag that v3 (or any of the earlier motion models) was trained on and can effectively respond to. I find myself doing...

I don't think the motion weights have been trained to work with SDXL ... but ... do you see any efforts to update everything to SDXL?

I see portrait videos on the cogvideox page

9

How were these portrait videos accomplished? Was it all post processing or can cogvideox I2V produce portrait now? https://yzy-thu.github.io/CogVideoX-demo/