@williamlocke6811

"The size of tensor a (64) must match the size of tensor b (96) at non-singleton dimension 4"

So at first I was getting the above error but after some tinkering I found that if I set resolution_x to 768 the video will then render. But at 512 I get the above error. Is that something you can easily fix with an update to your node? Or maybe there is something I can do?

The problem now is that when I was using your older node, I could get about 120 frames at 512. This was too short for my project. I become very excited to see you make a node that could render longer videos. But now at 768, that takes up a lot more VRAM so I can only get 100 frames (23.4GB of VRAM). Can't go much higher without OOM errors.

So, at least for me, your new LONG node is producing shorter videos than your older node ;)

I really hope there is an easy fix :) Anything you can think of to reduce the amount of VRAM needed would be VERY helpful.

@VibeAISongs

getting this msg while running the same, i did not get any output, but setting are same
Ready for inference.
Prompt executed in 101.45 seconds

plz anyone could find solution for me

@DuCaffeine

Brother, I watched your channel and I have two questions. The first question is, can I upload any video of mine that has a certain movement and will put it on a picture in a very professional manner? The second question is, give me a way to install it, please, brother. By the way, I am a new subscriber. Please, brother, take care of me 💯

@DuCaffeine

Give me the name of the form or workflow please.

@ParthKakarwar-b7j

when i installed the custom node,IT MESSED UP MY PYTORCH VERSION....
Can you plz help me how to get it working on my existing comfy UI  ,This is my system now, Total VRAM 4096 MB, total RAM 23903 MB
pytorch version: 2.3.1+cu121
xformers version: 0.0.27

@darshannilankar586

Can you provide me setting for rendering 20 sec video in HD quality

@ai.ulifeel

@Isi-uT , i have this error((((  UniAnimateImageLong
Unknown error

@williamsunstrider3364

I have been having issues getting any of the UniAnimate nodes to work at all. Any help would be appreciated. One of my errors reads as follows:    ReposeImage

Failed to init class <class 'ComfyUI-UniAnimate-W.tools.modules.clip_embedder.FrozenOpenCLIPTextVisualEmbedder'>, with PytorchStreamReader failed reading zip archive: failed finding central directory

@tanishqchahal9166

heyy, got this error while reposing an image "Failed to init class <class 'ComfyUI-UniAnimate-W.tools.modules.autoencoder.AutoencoderKL'>, with /usr/local/lib/python3.10/dist-packages/torchaudio/lib/libtorchaudio.so: undefined symbol: _ZNK3c105Error4whatEv". PLease help!!