NumZ comments

Results 42 comments of


                                            NumZ

[Bug]: use_video_mask doesn't effect image

same here, no effect

[feature request]It would be nice to add batch processing from a specific directory!

also ok, adding batch support will give awesome results

RuntimeError: Given groups=1, weight of size [320, 4, 3, 3], expected input[2, 9, 64, 64] to have 4 channels, but got 9 channels instead

same here with instructpix2pix model

[Bug]: with Deforum: TypeError: PlugableControlModel.init() got an unexpected keyword argument 'weight'

extacly same issue here

Suggestion to Extend Support for Comfy UI

Hiiii Thank you very much, I really appreciate 🙂 I'll try to do my best for do it faster that I can. I Let you know when ready Regards

RuntimeError: Detected that PyTorch and TorchAudio were compiled with different CUDA versions. PyTorch has CUDA version 11.8 whereas TorchAudio has CUDA version 11.7.

Hi, Sorry about that, It should works on ubunutu you can try : Go to you stable diffusion folder with terminal and activate your venv python (on windows venv\Scripts\activate but...

Installation failed, the error message is as follows! 安装失败，错误提示如下！

Hi, For some reson bark doesn"t install on 3.10 6, try to install python 3.10.11 Let me know Regards

Error with (save)

Hi, It seems to be an issue with numpy package, try to only select sd-wav2lip-uhq in extensions tab and apply and restart. Numpy can be use in several extensions. Let...

Not replacing previous mouth movements.

Hi On your demo video i can't see lot of extra motion...just few ones but not really visible... sorry...

Imcompatible issue for lower dependency env of wav2lip-uhp

Hi, The extension doesn't force tqdm version so I don't understand how that can came from sd-wav2lip-uhq Can you let me see the full logs please?