jy0205/LaVIT

Issues

• few questions

  #35 opened 16 days ago by ProjectDisR
  1

• quantize not working for motion

  #34 opened a month ago by ayaan-together
  4

• about motion

  #31 opened a month ago by 21157651
  1

• Training detail of codebook

  #29 opened a month ago by Faded1022
  1

• Training details of adding visual vocabs.

  #20 opened a month ago by martian422
  1

• can't find the file: data/coco/annotations/coco_t2i_eval.json

  #26 opened a month ago by yibin-mt
  1

• [Video-LaVIT] Objective function of the Tokenizers, Key Frame Detokenizer and Motion Condition Encoder

  #33 opened a month ago by Hesh0629
  2

• Finding a BUG in modeling_visual_encoder.py

  #32 opened a month ago by kabutohui
  1

• Request for Alternative to mvextractor Incompatible with CentOS

  #23 opened 2 months ago by patrick-tssn
  6

• Image generation with the multi-modal prompt

  #30 opened 3 months ago by haibo-qiu
  2

• Training detail of codebook

  #3 opened 10 months ago by sijeh
  4

• A question about motion vector

  #28 opened 4 months ago by xizaoqu
  2

• When will the training code of video-lavit be released?

  #27 opened 4 months ago by howardgriffin
  1

• A question regarding the performance boost of Video-LaVIT over LaVIT

  #25 opened 4 months ago by chenjy2003
  2

• Memory requirement of Video-LaVIT

  #21 opened 5 months ago by xizaoqu
  2

• RuntimeError: expected scalar type Float but found BFloat16

  #24 opened 4 months ago by patrick-tssn
  2

• Got noisy gif file

  #22 opened 5 months ago by lochuynh1412
  13

• When will the video-lavit code be released?

  #12 opened 5 months ago by howardgriffin
  11

• Can u release the training code?

  #17 opened 5 months ago by luohao123
  1

• How much graphics memory is required to use the latest weights to generate text images? (Mine is 3060, 12G, unable to load model weights at all)

  #18 opened 5 months ago by shams2023
  3

• Reproduce the reconsturction results of Fig. 7

  #19 opened 5 months ago by xizaoqu
  2

• Question about CIDEr score

  #15 opened 6 months ago by dusruddl2
  2

• Motion Vectors Dataloading

  #13 opened 6 months ago by PardoAlejo
  1

• annotation for InterVid-14M-aesthetics

  #14 opened 6 months ago by dreamerlin
  1

• whats the xformers version?

  #11 opened 7 months ago by gulegeji
  1

• question about the DYNAMIC VISUAL TOKENIZER

  #10 opened 7 months ago by bpwl0121
  4

• Issues running the model

  #8 opened 8 months ago by andysingal
  1

• Difference between the visual tokenizer for Generation task and Understanding tasks

  #9 opened 8 months ago by tedfeng424
  4

• Questions about the format of the training data

  #5 opened 10 months ago by trouble-maker007
  3

• Question about ViT

  #7 opened 10 months ago by SihengLi99
  5

• Question about the high-resolution pixel decoder

  #6 opened 10 months ago by SihengLi99
  2

• Finetuning Code

  #4 opened 10 months ago by yotofu
  1

• Training model

  #1 opened 10 months ago by Haonote
  4

• pretraing

  #2 opened 10 months ago by 20184490
  2