Xiang Li
Xiang Li
hi floringogianu, Thank you for making this pr. Would you like to explain why this `done = not (np.isfinite(state).all() or np.abs(state[1]) > .2)` can fix it? In my opinion, we...
hi @Weiney, Unfortunately, there is no further updating plan since current version can cover my own need. Could you please list some features that you expect? Maybe we can work...
https://ffmpeg.org/download.html
Have you ever experienced a similar issue when using the original client? If not, info like the output of the console, version of FFmpeg, and what OS you run might...
Thank you for the report, which looks very interesting. I'll try to figure it out.
Try `proxychain` if you can find a good proxy.
Hi @wassname Thank you for pointing it out and I believe you are correct. Based on my very limited observation, optimizing the encoder once per call didn't affect the performance...
Same here, it will be very helpful if you could release the decoder weights. Thanks a lot.
Same problem, help wanted. Thank you in advance.
Hi @cheng-chi , Thanks a lot for your response. I tried two versions: 1. Untouched training code from this repo (`diffusion_policy/workspace/train_diffusion_unet_hybrid_workspace.py`). 2. A simplified version whose core run function is...