YingqingHe / LVDM

LVDM: Latent Video Diffusion Models for High-Fidelity Long Video Generation

https://yingqinghe.github.io/LVDM/

YingqingHe/LVDM Issues

AttributeError: 'LatentDiffusion' object has no attribute 'resume_new_epoch'
Updated 8 months ago1
RuntimeError: Error(s) in loading state_dict for LatentDiffusion: Unexpected key(s) in state_dict: "cond_stage_model.transformer.text_model.embeddings.position_ids".
Updated 9 months ago
The quantitative results of reproduced generated samples and real samples are different with the LVDM official paper.
Updated 9 months ago1
Request for UCF pretrained weight
Updated 10 months ago
Total batch size of LVDM
Updated 10 months ago
Validation images not logging
Updated 10 months ago
what is the function of self.resume_new_epoch
Closed 10 months ago1
about prediction process
Closed 10 months ago
how to choose a suitable scale_factor and shift_factor?
Updated 10 months ago
Sky_lapse dataset structure
Updated a year ago1
Where can I find the InceptionI3D pre-training model in eval_cal_fvd_kvd?
Updated a year ago
GPU memory usage during training
Updated a year ago1
Error during training the AE
Closed a year ago1
Training code for the text2video generation?
Updated a year ago
When will the code be released?
Updated a year ago1
Different frame rates in WebVid
Updated a year ago
Code Release
Closed a year ago1
code release
Closed a year ago1