SHI-Labs/Versatile-Diffusion

Issues

• direct inference

  #37 opened 6 months ago by ShristiDasBiswas
  0

• ControlNet design

  #36 opened a year ago by gongzix
  0

• Is there a training repeat code

  #35 opened a year ago by LANSHANGH
  0

• ModuleNotFoundError: No module named 'lib.data_factory'

  #34 opened a year ago by sunny-rain-63
  0

• Error on running app.py

  #33 opened a year ago by gebaltso
  0

• I didn't find the inference.py file.

  #32 opened a year ago by Qusijia
  0

• example with ControlNet

  #27 opened 2 years ago by pribadihcr
  3

• In-painting

  #30 opened a year ago by hoosha
  0

• Zero-Shot Fid

  #20 opened 2 years ago by NieShenRuc
  2

• potential for data augmentation

  #29 opened 2 years ago by pribadihcr
  2

• About train code

  #15 opened 2 years ago by pokameng
  2

• When will the training code be released?

  #28 opened 2 years ago by pokameng
  1

• training code and the needed GPUs

  #26 opened 2 years ago by Daisy5296
  1

• closed

  #25 opened 2 years ago by wodsoe
  0

• when will release training code?

  #22 opened 2 years ago by pokameng
  3

• how to increase batch size

  #24 opened 2 years ago by demirklvc
  1

• If cudo finds only 1 device it crashes app.py immidietly

  #23 opened 2 years ago by Aultus-defora
  2

• Release VD-Basic

  #3 opened 2 years ago by litevex
  12

• Initializing from an image

  #14 opened 2 years ago by itjustis
  2

• About training part

  #18 opened 2 years ago by chenaoxuan
  2

• About watermark detection

  #21 opened 2 years ago by JingyeChen
  1

• 生成图片太亮

  #19 opened 2 years ago by yeqingzhao
  2

• integer division or modulo by zero

  #17 opened 2 years ago by forensicmike
  2

• How did you construct the paired data for text/image variation?

  #16 opened 2 years ago by shaform
  1

• when would the training codes can be released?

  #12 opened 2 years ago by runzeer
  1

• VersatileDiffusionPipeline - supported image variation inputs

  #11 opened 2 years ago by LukasStruppek
  2

• How much vram to run?

  #13 opened 2 years ago by wodsoe
  0

• Is there a way to specify text to image dimensions?

  #10 opened 2 years ago by dillfrescott
  2

• Relatedd VD official text variation

  #8 opened 2 years ago by sumantakcs
  1

• error when running inference script

  #7 opened 2 years ago by jmlongriver12
  1

• TypeError

  #6 opened 2 years ago by liuyongliuLYL
  1

• Image-to-text doesn't seem to work

  #5 opened 2 years ago by patrickvonplaten
  2

• ImportError fused_layer_norm_cuda.cpython-38-x86_64-linux-gnu.so:

  #4 opened 2 years ago by FrancescoSaverioZuppichini
  1

• can this already be ran?

  #2 opened 2 years ago by demirklvc
  3