YBYBZhang/ControlVideo

Issues

• Loading ckpt download web link is not available

  #36 opened 2 months ago by eunkyungYoo
  1

• Why not use conv3d directly

  #35 opened 4 months ago by EveningLin
  0

• pretrained file

  #34 opened 8 months ago by xua222
  1

• about the evaluate date

  #29 opened a year ago by FatLong666
  4

• First frame conditioning possible?

  #33 opened a year ago by ivaniliash
  2

• Combination with ip adpater

  #32 opened a year ago by pikeyang
  1

• nothing

  #31 opened a year ago by pikeyang
  0

• Evaluation Question: 125 Video-prompt Pairs

  #27 opened a year ago by mikolez
  2

• Is the same frame noise important?

  #30 opened a year ago by CHNxindong
  2

• Pure text generation

  #28 opened a year ago by QMME
  1

• Typo in NEG_prompt

  #25 opened a year ago by dhruvhacks
  2

• questions about loading ckpt

  #24 opened a year ago by koalaaaaaaaaa
  3

• problem with triton

  #15 opened a year ago by gonduras
  6

• ValueError: Calling CLIPTokenizer.from_pretrained() with the path to a single file or url is not supported for this tokenizer. Use a model identifier or the path to a directory instead.

  #23 opened a year ago by Rkunique
  0

• controlnet-aux==0.0.6 ValueError: depth is not a valid processor id

  #22 opened a year ago by CHNxindong
  2

• ValueError: mutable default <class 'timm.models.maxxvit.MaxxVitConvCfg'> for fie

  #20 opened a year ago by KaiJia2017
  1

• ERROR: Could not find a version that satisfies the requirement clip==1.0 (from versions: none) ERROR: No matching distribution found for clip==1.0

  #19 opened a year ago by KaiJia2017
  3

• CUDA out of memory

  #18 opened a year ago by Daybreak-Zheng
  1

• Single Character

  #17 opened a year ago by p0mad
  9

• The idea of full-frames attention shares a great similarity with the spatial-temporal modeling approach used in Vid2Vid-Zeros.

  #11 opened 2 years ago by jinxixiang
  3

• guide to run on kaggle or google collab

  #16 opened a year ago by sadath-12
  2

• no file named pytorch_model.bin, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory checkpoints/stable-diffusion-v1-5

  #5 opened 2 years ago by didoll-john
  5

• RuntimeError: The size of tensor a (24) must match the size of tensor b (12) at non-singleton dimension 2

  #14 opened a year ago by liuxz-cs
  3

• 请教大神

  #12 opened 2 years ago by xxxiaosong
  1

• The size of tensor a (30) must match the size of tensor b (16) at non-singleton dimension 2

  #9 opened 2 years ago by Laidawang
  1

• The input must have a source video?

  #10 opened 2 years ago by fistyee
  1

• smoother_step

  #8 opened 2 years ago by dlutzzw
  1

• cfa-vram

  #7 opened 2 years ago by dlutzzw
  2

• ask for help

  #4 opened 2 years ago by zcdliuwei
  1

• Excellent work

  #2 opened 2 years ago by 1171000410
  1

• Is 11GB GPU the minimum requirements?

  #1 opened 2 years ago by Njasa2k
  1

• The prompt seems wrong in Readme

  #3 opened 2 years ago by thuwzy
  1