lucidrains/imagen-pytorch

Issues

• Questions about Text-to-Image training

  #380 opened 5 months ago by xiaoxiaodadada
  2

• Backward problem with using DDP

  #375 opened a year ago by clearlyzero
  1

• Any specific reason sampling is not in FP16?

  #377 opened 10 months ago by danbochman
  2

• OutOfMemoryError

  #355 opened a year ago by nwoyecid
  3

• how to run this code, please provide the step for text to image , please

  #379 opened 8 months ago by rajnish159
  2

• Why not using CLIP ?

  #328 opened 2 years ago by axel588
  3

• train

  #341 opened 2 years ago by lijain
  1

• import Imagen returns BeartypeDecorHintParamDefaultViolation

  #378 opened 9 months ago by benjaminorr
  2

• NameError: name "model_validator" is not defined with version 1.26.1

  #376 opened a year ago by niklasbubeck
  1

• Question about Classifier-free Guidance

  #343 opened 2 years ago by lucala
  1

• Subprocess Error during Wheel Build: Missing File

  #372 opened a year ago by KillshotELOx
  0

• how to train your inpainting model using my own dataset？？

  #352 opened 2 years ago by dreamlychina
  1

• Samples after training only contain white noise.

  #347 opened 2 years ago by Valerie9696
  7

• GPU memory increases with the number of GPUs used

  #370 opened a year ago by DuanXiaoyue-LittleMoon
  0

• Why concatenate lowres before last conv?

  #369 opened a year ago by ifeherva
  0

• Super-resolution not completely respecting input low resolution image

  #367 opened a year ago by AhmedGamal411
  0

• Triton Python 3.10 and up

  #366 opened a year ago by Jammers33
  1

• Can anyone look over my script and see if I've made any errors?

  #365 opened a year ago by Shikamaru5
  0

• text prompts

  #364 opened a year ago by Shikamaru5
  0

• Question about reproducing training images using respective training texts

  #362 opened a year ago by AhmedGamal411
  0

• Question about retraining/fine-tuning EncoderModel with new words in `t5.get_tokenizer()`

  #358 opened a year ago by Kevin7720
  2

• how ta activate shuffle for DataLoader?

  #361 opened a year ago by TheZaind
  0

• Question about ConnectionError

  #360 opened a year ago by aoyang-hd
  0

• Correct Way to train both unets

  #354 opened a year ago by gauravbyte
  1

• Assert prevents mixed_precision?

  #357 opened a year ago by mattmisk
  3

• Pretrained Model

  #327 opened 2 years ago by wyfzka
  8

• Same Image whatever the input text on conditionnal train

  #316 opened 2 years ago by axel588
  1

• App para contratar servicios de eventos

  #353 opened 2 years ago by Vaalaadeez
  0

• Distributed Training Gets Stuck?

  #339 opened 2 years ago by pjspol
  1

• GPU memory usage VS GPU utilization

  #348 opened 2 years ago by kirilllzaitsev
  3

• trainer.train_ Incorrect use of step in text to video

  #350 opened 2 years ago by Ytimed2020
  0

• Visualization of the network

  #349 opened 2 years ago by kirilllzaitsev
  0

• How many images I need to generate an fine model

  #346 opened 2 years ago by liulwx
  1

• Can anyone reproduce the results of the paper?

  #344 opened 2 years ago by dreamlychina
  1

• Generated samples contain only noise while training unconditional Imagen

  #337 opened 2 years ago by lucala
  2

• text_embeds in trainer.sample() does not work properly

  #325 opened 2 years ago by bekhzod-olimov
  1

• Seek for advice to reproduce Gen-1

  #333 opened 2 years ago by liuquande
  1

• No such file or directory

  #342 opened 2 years ago by lijain
  0

• Inpainting with Videos (UNET3D)

  #338 opened 2 years ago by matvogel
  2

• Partial ignore time causes increased memory usage

  #320 opened 2 years ago by HReynaud
  2

• Working with images and text embeddings of different shape

  #336 opened 2 years ago by AhmedGamal411
  0

• multiple values for unet_number

  #335 opened 2 years ago by Shikamaru5
  1

• Num_Samples

  #334 opened 2 years ago by Shikamaru5
  0

• Text to video no Attentions layers

  #332 opened 2 years ago by axel588
  2

• Little issue, No module named 'lion_pytorch'

  #330 opened 2 years ago by axel588
  1

• ElucidatedImagen no text conditionning

  #329 opened 2 years ago by axel588
  2

• Loss flattens out after 50k training steps

  #324 opened 2 years ago by alif-munim
  1

• Decoder specified not to be conditioned on text, yet it is presented

  #323 opened 2 years ago by bekhzod-olimov
  0

• does image_embed_dim do anything?

  #318 opened 2 years ago by jaded0
  1

• Veryyy slow on 16x16, Text to Image, Training

  #317 opened 2 years ago by axel578
  0