generated video from sd3d_p is more than 20M and cannot be played
gracesolver opened this issue · comments
Follow the direction to generate 3d video from image. It can generate video, but it is more than 20M, cannot use player to play it. What is the problem in it ? Here is the executing output:
python scripts/sampling/simple_video_sample.py --input_path picture.png --version sv3d_p --elevations_deg 10.0
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
VideoTransformerBlock is using checkpointing
Initialized embedder #0: FrozenOpenCLIPImagePredictionEmbedder with 683800065 params. Trainable: False
Initialized embedder #1: VideoPredictionEmbedderWithEncoder with 83653863 params. Trainable: False
Initialized embedder #2: ConcatTimestepEmbedderND with 0 params. Trainable: False
Initialized embedder #3: ConcatTimestepEmbedderND with 0 params. Trainable: False
Initialized embedder #4: ConcatTimestepEmbedderND with 0 params. Trainable: False
Restored from checkpoints/sv3d_p.safetensors with 0 missing and 0 unexpected keys
/home/xxxxxx/.local/lib/python3.10/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
