JorgeR81

Results 193 comments of JorgeR81

> 2. Sorry this is missing - but you can just ctrl + drag over the group and press delete OK, thanks ! I didn't know about this workaround.

A better behavior would be to hide parameter's name instead. 

The issues are being submitted in the custom node page. https://github.com/comfyanonymous/ComfyUI_bitsandbytes_NF4

InstantX is so large ( 7 GB ) in comparison with XLabs-AI ( 1.5 GB ) ! It may not work for lower end systems which can currently run Flux....

> It works on controlnet weight 0.9 above, just works. waiting for better quality. The pose seems good, but it seems it got more of an illustration style, with the...

I have a GTX 1070 ( 8GB ) Using  `--force-fp32` also improves my inference speed ( by about 50% ) While the fp8 model is loading it needs to be...

( Github just went down for a while here ) Anyways, I think I've found why this is slower for us, on a Pascal GPU https://forums.developer.nvidia.com/t/fp16-support-on-gtx-1060-and-1080/53256/2 > All GPUs with...

This may need some tweaks to work on my old GTX 1070 ( 8GB ) Even with `--reserve-vram 1.2`, and Flux FP8, the GPU activity spikes to 100%, even before...

I have the same error with the Flux Realism Lora https://huggingface.co/XLabs-AI/flux-RealismLora

> > I have the same error with the Flux Realism Lora https://huggingface.co/XLabs-AI/flux-RealismLora > > Take a look at this: > https://huggingface.co/comfyanonymous/flux_RealismLora_converted_comfyui It works. Thanks !