thu-ml/unidiffuser

Issues

• About training codes

  #4 opened 2 years ago by pokameng
  4

• Does unidiffuser support using the peft library for lora fine-tuning？

  #32 opened a year ago by zdxff
  1

• Training uvit

  #38 opened a year ago by Jihyeon-Je
  2

• can' t load tokenizer for 'gpt2', why?

  #21 opened 2 years ago by mxwcqu
  5

• May I ask what validation loss you used during training?

  #37 opened a year ago by gao131
  0

• Unidiffuser can not be loaded in the latest version of diffusers

  #36 opened a year ago by javyduck
  1

• expected str, bytes or os.PathLike object, not NoneType

  #29 opened a year ago by LKJ-np
  1

• Generated images using diffusers package code in README are completely black

  #34 opened a year ago by SKDDJ
  2

• Question about encoding images and texts

  #33 opened a year ago by xiaotingxuan
  2

• question about training

  #35 opened a year ago by Guardian-in-the-WF
  1

• How to reproduce CLIP score

  #31 opened a year ago by ofzlo
  0

• requests.exceptions.ConnectionError: ('Connection aborted.', ConnectionResetError(104, 'Connection reset by peer'))

  #30 opened a year ago by LKJ-np
  0

• Some questions about training u-vit

  #18 opened 2 years ago by ximinng
  2

• How to fine-tune the Unidiffusier?

  #27 opened 2 years ago by 6Roy
  1

• urlopen error [Errno 104] Connection reset by peer

  #26 opened 2 years ago by runtoforever
  0

• question about training

  #25 opened 2 years ago by jzssz
  0

• Have you ever trained LAION-5B on other smaller version of U-ViT? Huge, Large or Small ?

  #24 opened 2 years ago by nemonameless
  0

• Hello, how do I train unidiffuser or finetune on an existing model?

  #23 opened 2 years ago by jzssz
  0

• Some questions about unidiffuser paper

  #14 opened 2 years ago by orchidmalevolence
  4

• Is it possible that use a convolution Unet to predict the joint distrubution?

  #22 opened 2 years ago by shencuifeng
  0

• Hi! A little question about the text length limit

  #20 opened 2 years ago by StanLiu1996
  1

• The State of the Model and Future Updates

  #17 opened 2 years ago by LeoXing1996
  0

• About training cost and model size

  #10 opened 2 years ago by sunyoe
  4

• image interpolation

  #16 opened 2 years ago by loboere
  1

• When will you release the training codes?

  #15 opened 2 years ago by nemonameless
  0

• is the model support chinese prompt?

  #12 opened 2 years ago by hrdxwandg
  1

• Supporting partial image sampling like in img2img

  #11 opened 2 years ago by reesekneeland
  0

• Information of computing power consumption

  #1 opened 2 years ago by Boatsure
  2

• Question on License

  #6 opened 2 years ago by cloneofsimo
  1

• How to finetune unidiffuser

  #5 opened 2 years ago by dawei03896
  1

• 复现代码报错，请求解决

  #2 opened 2 years ago by 745165806
  4

• Mac M1 support

  #3 opened 2 years ago by AugustRush
  0