ByteDance-Seed / ByteDance-Seed/SeedVR
SeedVR2 所谓 "from scratch" 从头训练，是从随机参数训练，还是从预训练的视频模型进行训练的？
Open
- Dominant language
- Python
- Stars
- 1.4k
- Forks
- 82
- PR merge metrics
- No merged PRs in 30d
Description
论文中提到 seedvr2 从头训练的 seedvr， 请问下是从随机参数直接开始训练的吗？
> We first train a 7B SeedVR model (Wang
et al., 2025) from scratch following the new attention design in this paper. Then, we initialize the
model parameters from 7B SeedVR model and follow the training strategies discussed in Sec. 3.3
for our SeedVR2 models.
Contributor guide
No contributing guide indexed for this repository
Assessment
This issue has not been assessed yet.