ali-vilab/videocomposer

Issues

• Xformers

  #45 opened 6 months ago by suimuc
  0

• only text+image generation

  #28 opened 2 years ago by WongChen
  2

• 根据配置文件安装环境报错

  #15 opened 2 years ago by liaogulou
  8

• Video inpainting using a sequence of masks

  #40 opened a year ago by AHHHZ975
  3

• cannnot install/import flash_attn

  #44 opened a year ago by yukyeongmin
  1

• Text + SingleImage not right

  #10 opened 2 years ago by wangxihao
  2

• CUDA error: no kernel image is available for execution on the device

  #14 opened 2 years ago by liuxz-cs
  4

• How to modify the resolution of generated video?

  #43 opened a year ago by sheldonn2
  1

• How to adjust parameters to ensure consistent output video multiple times?

  #42 opened a year ago by Yinhance
  0

• about the script of I2V generation

  #41 opened a year ago by XiaoyuShi97
  0

• Error while processing rearrange-reduction pattern "(i j) c f h w -> c f (i h) (j w)". Input tensor shape: torch.Size([3, 16, 256, 256]). Additional info: {'i': 1}.

  #12 opened 2 years ago by Yaomingshuai
  10

• The error when install the flash-attn

  #32 opened 2 years ago by mayuelala
  3

• The download for the model weights isn't working.

  #20 opened a year ago by Njasa2k
  0

• Some questions about STC encoder

  #39 opened a year ago by Daming-TF
  1

• About hand crafted motion guidance

  #33 opened 2 years ago by emjay73
  1

• Question about extracting the different conditions

  #38 opened a year ago by YujieOuO
  3

• Question about Rescaling `noise` according to `guidance_rescale`

  #37 opened a year ago by OliviaWang123456
  1

• How to train the model

  #34 opened 2 years ago by BooHwang
  3

• looking forward to the open source of trainning code

  #35 opened 2 years ago by TediousBoredom
  1

• plan for releasing the training code?

  #36 opened a year ago by forever208
  1

• Can you share bash command about "A moving golden moon" case?

  #31 opened 2 years ago by YuyangYin
  0

• not found for model **ViT-H-14.**

  #29 opened 2 years ago by woozheng
  1

• 有关于 damo-vilab/MS-Vid2Vid-XL 的参考资料吗？

  #30 opened 2 years ago by svjack
  1

• the running script for “Text,style,hand-crafted motions and hand-carfted sketch”

  #11 opened 2 years ago by wintercat1994
  2

• fvd performance on MSR-VTT

  #16 opened 2 years ago by jinxixiang
  2

• hand-crafted motions and hand-crafted sketch

  #24 opened 2 years ago by hzlhzlhzlhzl
  1

• How was the pretraining dataset Laion-400M used ? does this actually refer to the use of the ‘open_clip_pytorch_model’ from OPENCLIP ?

  #25 opened 2 years ago by BaiqiangGit
  1

• How to Achieve Video Inpainting？

  #23 opened 2 years ago by 90duyangwang
  1

• support for other resolutions

  #26 opened 2 years ago by maximepeabody
  1

• killed

  #27 opened 2 years ago by Source419
  0

• metric-related

  #22 opened 2 years ago by zhw-zhang
  0

• torch.multiprocessing.spawn.ProcessExitedException: process 2 terminated with signal SIGSEGV

  #21 opened 2 years ago by zzningxp
  2

• When will the code be fully released? Thank you.

  #2 opened 2 years ago by HUAFOR
  3

• the running script for “sequence-to-video generation”

  #19 opened 2 years ago by lu123456789
  0

• GLIBC_2.32 not found

  #18 opened 2 years ago by jwb95
  0

• Code update

  #13 opened 2 years ago by rakesh-reddy95
  0

• Keypoin or skelton video generation!

  #4 opened 2 years ago by p0mad
  4

• Training code

  #3 opened 2 years ago by julkaztwittera
  2

• RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu)

  #9 opened 2 years ago by XuejiFang
  5

• ResolvePackageNotFound

  #7 opened 2 years ago by magicwang1111
  2

• 计算代价询问

  #6 opened 2 years ago by aopolin-lv
  2

• cannot install motion-vector-extractor

  #8 opened 2 years ago by FunnyClown
  1

• .

  #5 opened 2 years ago by JacobYuan7
  0

• Will this be unreleased because of audits?

  #1 opened 2 years ago by Njasa2k
  1