AnimateDiff

AnimateDiff copied to clipboard

⭐⭐⭐⭐⭐ Claude 3 - architectual redesign POC suggestion 100X - faster training / inference times / reduced parameters / mem footprint

1

https://paperswithcode.com/method/depthwise-separable-convolution#:~:text=While%20standard%20convolution%20performs%20the,a%20linear%20combination%20of%20the current setup   https://youtu.be/vVaRhZXovbw Among the architecture redesign options mentioned, using efficient blocks, specifically depthwise separable convolutions, is probably the easiest to...

johndpope

TypeError: EulerDiscreteScheduler.__init__() got an unexpected keyword argument 'steps_offset'

1

Traceback (most recent call last): File "/root/miniconda3/envs/animatediff/lib/python3.10/site-packages/gradio/routes.py", line 534, in predict output = await route_utils.call_process_api( File "/root/miniconda3/envs/animatediff/lib/python3.10/site-packages/gradio/route_utils.py", line 226, in call_process_api output = await app.get_blocks().process_api( File "/root/miniconda3/envs/animatediff/lib/python3.10/site-packages/gradio/blocks.py", line 1550, in...

wangxin1999

Traceback (most recent call last): File "/data/AnimateDiff-main/train.py", line 495, in main(name=name, launcher=args.launcher, use_wandb=args.wandb, **config) File "/data/AnimateDiff-main/train.py", line 130, in main local_rank = init_dist(launcher=launcher) File "/data/AnimateDiff-main/train.py", line 48, in init_dist rank...

traveling121

AttributeError: 'Row' object has no attribute 'style'

1

A matching Triton is not available, some optimizations will not be enabled. Error caught was: No module named 'triton' Traceback (most recent call last): File "/app/AnimateDiff/app.py", line 327, in demo...

12441409

Why does unet_use_temporal_attention and unet_use_temporal_attentionis are always None or False?

2

Why does unet_use_temporal_attention and unet_use_temporal_attention are always None or False? It seems not woking in temporal attention. Does anyone know about this? Thx!

liutaocode

Thanks to the author for his work! When will the training code of SparseCtrl be released?

song-wensong

"AssertionError"

3

(animatediff) PS F:\animediff\AnimateDiff> python -m scripts.animate --config configs/prompts/1-ToonYou.yaml C:\Users\dbodbo\miniconda3\envs\animatediff\lib\site-packages\torchvision\io\image.py:13: UserWarning: Failed to load image Python extension: Could not find module 'C:\Users\dbodbo\miniconda3\envs\animatediff\Lib\site-packages\torchvision\image.pyd' (or one of its dependencies). Try using the full...

dbodbo

Why encoder_hidden_state is used in the motion module?

3

Can you explain why encoder_hidden_state is used in the motion module? The motion module as expressed in the paper is a vanilla temporal attention, not cross-attention.  https://github.com/guoyww/AnimateDiff/blob/cf80ddeb47b69cf0b16f225800de081d486d7f21/animatediff/models/unet_blocks.py#L411

junwenxiong

Could you please explain the differences between v1, v2 and v3 versions? Thanks

1

I want to train animatediff, but I found that only the v1 version of the pre-trained model can be loaded in the current code?

zhangjinyangnwpu

Can you provide the supplementary material about the paper SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models?

LiuhanChen-github