MythicalChu
MythicalChu
The official one is out: https://github.com/TencentQQGYLab/ComfyUI-ELLA
I got it working; installed torch_directml manually, but also had to add "args.skip_torch_cuda_test = True" inside prepare_environment() in modules/launch_utils.py, since the startup was not actually recognizing the flag "--skip-torch-cuda-test" (even...
Yes, recent changes broke more things for Directml, I've mentioned them, and a workaround for us, here: https://github.com/lllyasviel/stable-diffusion-webui-forge/issues/73
> RuntimeError: Device type privateuseone is not supported for torch.Generator() api. RuntimeError: 'devices' argument must be DML (in cmd) > > i did all steps but I have this error,...
> > Yes, recent changes broke more things for Directml, I've mentioned them, and a workaround for us, here: #73 > > That works for ipadapter I was the original...
Generation is frozen on the/before the 1st step now. Maybe it's the same (old torch) bug that ComfyUI's Ip-adapter has: sigma_t = sigmas[index].item() , the var can't be read. here's...
btw, the same problem happens on Kohya Deep Shrink, so I noticed that the file \ldm_patched\contrib\external_model_downscale.py has an almost identical line: sigma = transformer_options["sigmas"][0].item() treating it the same way as...
The recent changes to the Ip-adapter code still freeze Directml. I'm not sure if it was intentional or a typo, but the current line is different from the discussed one:...
I use Opera and this never worked for me
I second this