NVlabs/edm issues and pull requests

#30 - Error in stride shape

Issue - State: open - Opened by Mxdy21 2 months ago - 1 comment

#29 - Backward incompatible changes in huggingface_hub

Issue - State: closed - Opened by rafalkarczewski 3 months ago

#28 - Using EDM for end-to-end training of latent diffusion models

Issue - State: open - Opened by pandekan 6 months ago

#28 - Using EDM for end-to-end training of latent diffusion models

Issue - State: open - Opened by pandekan 6 months ago

#27 - Question about Fourier Embedding and EDM Loss calculation

Issue - State: closed - Opened by zhengyu-su 7 months ago - 1 comment

#26 - Is it possible to also share the code for Figure 1b (ideal denoiser outputs) in the paper

Issue - State: open - Opened by tien-th 9 months ago

#25 - AssertionError: Torch not compiled with CUDA enabled

Issue - State: closed - Opened by pierrelouisdelx 11 months ago

#25 - AssertionError: Torch not compiled with CUDA enabled

Issue - State: closed - Opened by pierrelouisdelx 11 months ago

#24 - About hyper-parameters selection

Issue - State: open - Opened by JincanDeng 11 months ago

#24 - About hyper-parameters selection

Issue - State: open - Opened by JincanDeng 11 months ago

#23 - Different Phases of Sampling

Issue - State: open - Opened by coopersvajda almost 1 year ago

#23 - Different Phases of Sampling

Issue - State: open - Opened by coopersvajda almost 1 year ago

#22 - On checkpoint for 256*256 images

Issue - State: open - Opened by mengxiangming about 1 year ago

#22 - On checkpoint for 256*256 images

Issue - State: open - Opened by mengxiangming about 1 year ago

#21 - Question about parameter tuning

Issue - State: open - Opened by xiong-creator about 1 year ago - 1 comment

#21 - Question about parameter tuning

Issue - State: open - Opened by xiong-creator about 1 year ago - 1 comment

#20 - Score calculation

Pull Request - State: closed - Opened by rrevoid about 1 year ago

#20 - Score calculation

Pull Request - State: closed - Opened by rrevoid about 1 year ago

#19 - Fast sampling

Pull Request - State: closed - Opened by daniil-shlenskii about 1 year ago

#19 - Fast sampling

Pull Request - State: closed - Opened by daniil-shlenskii about 1 year ago

#18 - ERROR when using multi-gpu training

Issue - State: closed - Opened by tsWen0309 about 1 year ago - 7 comments

#17 - Question about Augmentation

Issue - State: open - Opened by hojaeklee about 1 year ago - 1 comment

#17 - Question about Augmentation

Issue - State: open - Opened by hojaeklee about 1 year ago - 1 comment

#16 - Can not reproduct the result in Table 2.

Issue - State: open - Opened by Zyriix about 1 year ago - 5 comments

#15 - Could you please provide us imagenet-uncond checkpoint?

Issue - State: open - Opened by huanranchen over 1 year ago

#14 - About the Checkpoint

Issue - State: open - Opened by SYZhang0805 over 1 year ago

#13 - VP checkpoints are trained using VE-scaling?

Issue - State: closed - Opened by huanranchen over 1 year ago - 2 comments

#13 - VP checkpoints are trained using VE-scaling?

Issue - State: closed - Opened by huanranchen over 1 year ago - 2 comments

#12 - Is it possible to also share the code for Figure 3 in the paper

Issue - State: closed - Opened by yuanzhi-zhu over 1 year ago - 1 comment

#12 - Is it possible to also share the code for Figure 3 in the paper

Issue - State: closed - Opened by yuanzhi-zhu over 1 year ago - 1 comment

#11 - params[x] in this process with sizes [x, x] appears not to match sizes of the same param in process 0

Issue - State: closed - Opened by forever208 over 1 year ago - 2 comments

#10 - Fixed modes

Pull Request - State: closed - Opened by KevinRojas1499 almost 2 years ago

#10 - Fixed modes

Pull Request - State: closed - Opened by KevinRojas1499 almost 2 years ago

#9 - Is the original loss of VP/VE implemented (i.e. network predict epsilon)?

Issue - State: closed - Opened by forever208 almost 2 years ago - 1 comment

#9 - Is the original loss of VP/VE implemented (i.e. network predict epsilon)?

Issue - State: closed - Opened by forever208 almost 2 years ago - 1 comment

#8 - .

Issue - State: closed - Opened by philgzl almost 2 years ago

#7 - DataLoader worker (pid xxxx) is killed by signal

Issue - State: closed - Opened by Zhendong-Wang almost 2 years ago - 1 comment

#7 - DataLoader worker (pid xxxx) is killed by signal

Issue - State: closed - Opened by Zhendong-Wang almost 2 years ago - 1 comment

#6 - How to select options shown in Table2 for training VP/VE models

Issue - State: open - Opened by MingyuKim87 about 2 years ago - 1 comment

#6 - How to select options shown in Table2 for training VP/VE models

Issue - State: open - Opened by MingyuKim87 about 2 years ago - 1 comment

#5 - Wrong beta_D coefficient for VP during sampling?

Issue - State: open - Opened by qiyan98 about 2 years ago - 1 comment

#5 - Wrong beta_D coefficient for VP during sampling?

Issue - State: open - Opened by qiyan98 about 2 years ago - 1 comment

#4 - Deterministic sampling and sampling steps

Issue - State: open - Opened by FutureXiang about 2 years ago

#3 - Zero initialization of convolutions

Issue - State: open - Opened by nicolas-dufour about 2 years ago - 1 comment

#2 - Possible error in the up-sampling function

Issue - State: closed - Opened by Msadat97 about 2 years ago - 1 comment

#1 - Question about the parameterizations of VP-SDE

Issue - State: closed - Opened by FutureXiang about 2 years ago - 1 comment

GitHub / NVlabs/edm issues and pull requests