microsoft/VQ-Diffusion

Issues

• How to get quantized latents (indices)?

  #50 opened a month ago by AmitMY
  1

• Try using UC_DALLE to train on cifar10 dataset

  #49 opened a month ago by twq0105
  0

• is it normal to take 20mins to get a result?

  #45 opened 7 months ago by Moming0215
  1

• Why VQGAN ？

  #48 opened 2 months ago by zyx20030325
  0

• KeyError: 'norm_type' When Using Diffusers pipeline

  #47 opened 2 months ago by PoisonKiller
  0

• About the training of CUB200 dataset

  #41 opened a year ago by DZY-irene
  5

• Calculation of q_posterior?

  #20 opened 2 years ago by PanXiebit
  7

• device-side assert triggered

  #29 opened 2 years ago by zideliu
  3

• How to train VQVAE models? Can you provide the training configuration file for training vqvae?

  #46 opened 6 months ago by 353xiong
  0

• download links are invalid

  #44 opened 7 months ago by Moming0215
  1

• Having problem downloading pretrained models

  #43 opened 8 months ago by yuripetralia
  0

• How do you prevent generating [MASK] token at the last step

  #18 opened 2 years ago by cantabile-kwok
  1

• How to train VQVAE models?

  #42 opened 10 months ago by mducducd
  0

• About the proof of introducing a small uniform noise helps preventing trivial posterior.

  #40 opened a year ago by Ma-Weijian
  1

• About the pictures generated by the cub data set, there is white fog

  #39 opened a year ago by 623851394
  1

• CUB dataset

  #16 opened 2 years ago by ZeWang95
  3

• RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

  #38 opened a year ago by Paperbackpeople
  1

• Unable to train in >1 GPU

  #37 opened a year ago by pravn
  0

• Lt_sqrt[0] = Lt_sqrt[1] # Overwrite decoder term with L1.

  #36 opened a year ago by wanghanxiao123
  0

• Difference from LDM

  #35 opened a year ago by Tsingularity
  1

• Hugging face API in the readme needs to be updated.

  #30 opened 2 years ago by zzzc18
  1

• Hi, Can you update checkpoints again, the links looks died. Thanks

  #33 opened 2 years ago by Frreed
  0

• how to convert onnx？

  #32 opened 2 years ago by leesuga
  0

• Inference with VQ-VAE models

  #31 opened 2 years ago by toshi2k2
  0

• Filter Ratio when Sample?

  #1 opened 3 years ago by sunyasheng
  3

• How to implement the irregular mask inpainting results

  #28 opened 2 years ago by saga1214
  0

• About unconditional synthesis on FFHQ.

  #27 opened 2 years ago by Godkimchiy
  0

• cannot reproduce inference using coco_pretrained.pth

  #12 opened 2 years ago by Lizb6626
  2

• Cannot run training script on single GPU

  #17 opened 2 years ago by quqixun
  0

• Equations in the original paper

  #25 opened 2 years ago by fido20160817
  0

• text-guide image editing?

  #22 opened 2 years ago by fido20160817
  0

• Change the dimension of the input and ouptu image

  #21 opened 2 years ago by ClinicalAI
  0

• How to inference ffhq with classifier-free sampling

  #19 opened 2 years ago by jackiezhang11
  0

• Progress toward Google Colab with Inference Error

  #3 opened 2 years ago by metaphorz
  4

• File "taming_f8_8192_openimages_last.pth" not found?

  #5 opened 2 years ago by 1069066484
  1

• This repo is missing important files

  #14 opened 2 years ago by microsoft-github-policy-service
  1

• q_posterior computation

  #15 opened 2 years ago by naoto0804
  0

• Some parameters don't receive gradients.

  #6 opened 2 years ago by guyuchao
  2

• Cannot reproduce FID on Imagenet.

  #7 opened 2 years ago by guyuchao
  0

• State-of-the-art comparison

  #4 opened 3 years ago by xl-sr
  2

• Cannot download the pretrained model

  #2 opened 3 years ago by metaphorz
  2