edwin zeng

I am having the OOM issue as well. Previously, I have no problems running DynamiCrafter on my 8gb vram GPU. Today, I tried running it and it kept saying OOM....

I found out that a fresh installation of ComfyUI now uses torch 2.3.0, which has no compatible version of xformers, so the log complained that I had no xformers installed....

I was trying CPU mode but I got this error for the BoostingMonocularDepth: `Traceback (most recent call last): File "C:\tools\3d-photo-inpainting\BoostingMonocularDepth\run.py", line 580, in run(dataset_, option_) File "C:\tools\3d-photo-inpainting\BoostingMonocularDepth\run.py", line 48, in...

After updating ComfyUI for SD35L, it appears that the t5_attention_mask attribute cannot be accessed in SD3ClipModel. So the PixArt T5 from SD3 Clip, which outputs T5, cannot be used to...

Ok I found out what the error was now, after checking the latest sd.py. It used "if clip_type == CLIPType.SD3:" as the conditional. So I had to select 'sd3' as...

I need to add some features too as I had been using PixArt-Sigma and found some success with it. 1) Achieve a similar midjourney-style aesthetic quality, currently found in PixArt-Sigma....

> @doogyhatts please do not have aesthetic locking, since coming from the SDXL derivative side of things, people have really put in effort to make everything aesthetically flexible. Simply have...

To resolve this issue, I remembered reinstalling torch, torchvision, and torchaudio directly after activating the virtual environment. But yes, the dependency requirements are not accurate. So I had to redo...

> @doogyhatts Could you share which versions of the installed packages (torch, torchvision, torchaudio) you are using? torch 2.3.1+cu121 torchvision 0.18.1+cu121 torchaudio 2.3.1+cu121 xformers 0.0.27

Just tested running a Hunyuan Video workflow on an 7900XTX. Unfortunately, it hung on the vae decode (tiled) node.