bash scripts/autoregressive/extract_codes_c2i.sh --vq-ckpt ./pretrained_models/vq_ds16_c2i.pt --data-path /path/to/imagenet/train --code-path /path/to/imagenet_code ...
🔥 FAR leverages clean visual context without additional image-to-video fine-tuning: Unconditional pretraining on UCF-101 achieves state-of-the-art results in both video generation (context frame = 0) ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback