soumik-kanad/diff2lip

Issues

• i model's checkpoints are miss matched and dont worked

  #42 opened 10 days ago by SKY-CELLINIUM
  1

• Can you give weights of each loss in total?

  #41 opened 2 months ago by pvthienn
  1

• Feature request: Add some sort of progress % or meter

  #40 opened 3 months ago by LuckyNES
  0

• RuntimeError: module compiled against ABI version 0x1000009 but this version of numpy is 0x2000000

  #39 opened 3 months ago by LuckyNES
  2

• Hi can you tell me how to to remove the aritifacts around lips

  #38 opened 3 months ago by Utk-bot
  2

• Low res result for single video inference (especially for the teeth area).

  #17 opened 10 months ago by loic-combis
  6

• About inference video effects

  #37 opened 4 months ago by zhanghongyong123456
  2

• Docker

  #36 opened 4 months ago by M3chaKret
  0

• Running on mac m1

  #35 opened 4 months ago by keystabbs
  3

• How to inference for a audio video pair, please let me know simply what need to be done?

  #34 opened 4 months ago by QuantumShot10
  1

• can you help

  #18 opened 10 months ago by zachysaur
  7

• Is this project still active?

  #33 opened 4 months ago by HppZ
  6

• Would you consider sharing the training code

  #12 opened 5 months ago by xyh19960622
  1

• Inference in Windows

  #16 opened 5 months ago by crockrocks
  4

• training code?

  #9 opened a year ago by timnlupo
  1

• Will you include training code?

  #20 opened 5 months ago by shahidmuneer
  1

• I can't install

  #24 opened 5 months ago by Chechgroup
  0

• create model failed

  #25 opened 5 months ago by TANGnlp0711
  1

• Information about GAN loss

  #27 opened 5 months ago by agokrani
  3

• when finally write the video,it turn out the index error

  #28 opened 5 months ago by like-yo
  2

• GPU not being used

  #31 opened 5 months ago by amirhamdani
  1

• i am stuck here

  #19 opened 5 months ago by zachysaur
  9

• ollama

  #32 opened 5 months ago by M3chaKret
  1

• Train Code ?

  #14 opened 6 months ago by AMEERAZAM08
  3

• ValueError: Could not determine output format

  #30 opened 6 months ago by filippobartolucci
  1

• RuntimeError: CUDA error: an illegal memory access was encountered

  #29 opened 7 months ago by Hyp0x3mia
  0

• Setting diffusion steps to > 1000 introduces Gaussian noise

  #26 opened 8 months ago by xjtuljy
  1

• the model is not matched,i do not konw why

  #21 opened 9 months ago by chencong-source
  1

• possible to only get the differential output?

  #23 opened 9 months ago by DrBrule
  2

• the single result lip sync video seems not so good

  #6 opened a year ago by Wild-Piggggggg
  16

• Issue about https://github.com/cloneofsimo/lora/issues/258

  #22 opened 10 months ago by BeALigh
  1

• Result Video blurry

  #13 opened 10 months ago by wfengchen
  1

• Inference in Windows?

  #15 opened 10 months ago by crockrocks
  0

• About temporal consistency

  #11 opened a year ago by chunyu-li
  1

• RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'

  #10 opened a year ago by remiconext
  1

• When will release the code?

  #1 opened a year ago by junwenxiong
  7

• Process killed

  #8 opened a year ago by printerwhale
  4

• Extremely distorted video for reconstruction and cross.

  #3 opened a year ago by constan1
  3

• Diffusion iterations

  #7 opened a year ago by NikitaKononov
  1

• about infer my own video? have error ?

  #4 opened a year ago by zhanghongyong123456
  3

• is this support higher resolution face clip size?

  #5 opened a year ago by xpeng
  1

• t, the shape in current model is torch.Size([256]). size mismatch for out.2.weight: copying a param with shape torch.Size([6, 128, 3, 3]) from checkpoint, the shape in current model is torch.Size([3, 128, 3, 3]).

  #2 opened a year ago by constan1
  2