lbdave94
lbdave94
hi @Ezrealz , did you solve it?
@betterze hi, no I didn't. **IMO** they should be accurately picked with special attention to noise level. Since the student will learn to generate the image in a single step,...
@digbangbang the teacher model is a classic DM that has learned already to go from pure noise to clean image. It's correct that it has 1000 steps. The problem with...
@YinonDouchanClarity @rainbowoldhorse did you solve somehow?
Hi @sahreen-haider , did you solve the problem somehow? I have problem for a video where the speaker is talking with accentuated expressions and is he is in the foreground....
@yxlu-0102 to extend bandwidth properly from 24kHz to 48kHz we have to run `python inference_16k.py` or `python inference_48k.py` ?