hum_ma

Results 4 comments of hum_ma

The recent UI update made simple actions more complicated

Thanks @without-ordinary for the info, it's good to have a static, visible cancel button. However, the pop-up still shows up when I go near the upper right part of the...

[Performance Regression] GGUF models run noticeably slower with only ~50% VRAM usage after removing WAN Block Swap node (compared to previous manual offloading behavior at 80-90% VRAM)

I'm experiencing an extreme slow-down with ComfyUI 0.3.76 with a workflow which does nothing else but loads a umt5 Q4 GGUF CLIP to device cuda:0 (MultiGPU node), encodes a text...

[Performance Regression] GGUF models run noticeably slower with only ~50% VRAM usage after removing WAN Block Swap node (compared to previous manual offloading behavior at 80-90% VRAM)

> > I'm experiencing an extreme slow-down with ComfyUI 0.3.76 with a workflow which does nothing else but loads a umt5 Q4 GGUF CLIP to device cuda:0 (MultiGPU node), encodes...

[Performance Regression] GGUF models run noticeably slower with only ~50% VRAM usage after removing WAN Block Swap node (compared to previous manual offloading behavior at 80-90% VRAM)

> We fixed two bugs in clip loading today so hopefully your flows work better. Feel free to pull latest git or let us know once 3.77 comes. I applied...