Issues
- 1
few questions
#35 opened by ProjectDisR - 4
quantize not working for motion
#34 opened by ayaan-together - 1
about motion
#31 opened by 21157651 - 1
Training detail of codebook
#29 opened by Faded1022 - 1
Training details of adding visual vocabs.
#20 opened by martian422 - 1
- 2
[Video-LaVIT] Objective function of the Tokenizers, Key Frame Detokenizer and Motion Condition Encoder
#33 opened by Hesh0629 - 1
Finding a BUG in modeling_visual_encoder.py
#32 opened by kabutohui - 6
- 2
Image generation with the multi-modal prompt
#30 opened by haibo-qiu - 4
Training detail of codebook
#3 opened by sijeh - 2
A question about motion vector
#28 opened by xizaoqu - 1
- 2
- 2
Memory requirement of Video-LaVIT
#21 opened by xizaoqu - 2
- 13
Got noisy gif file
#22 opened by lochuynh1412 - 11
When will the video-lavit code be released?
#12 opened by howardgriffin - 1
Can u release the training code?
#17 opened by luohao123 - 3
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 by shams2023 - 2
Reproduce the reconsturction results of Fig. 7
#19 opened by xizaoqu - 2
Question about CIDEr score
#15 opened by dusruddl2 - 1
Motion Vectors Dataloading
#13 opened by PardoAlejo - 1
annotation for InterVid-14M-aesthetics
#14 opened by dreamerlin - 1
whats the xformers version?
#11 opened by gulegeji - 4
question about the DYNAMIC VISUAL TOKENIZER
#10 opened by bpwl0121 - 1
Issues running the model
#8 opened by andysingal - 4
Difference between the visual tokenizer for Generation task and Understanding tasks
#9 opened by tedfeng424 - 3
- 5
Question about ViT
#7 opened by SihengLi99 - 2
- 1
Finetuning Code
#4 opened by yotofu - 4
Training model
#1 opened by Haonote - 2