Stoobs

Just ran into this tonight, error on the console was: `File "F:\stable-diffusion-webui\modules\sd_samplers.py", line 377, in sample_img2img return self.func(self.model_wrap_cfg, xi, sigma_sched, extra_args={'cond': conditioning, 'uncond': unconditional_conditioning, 'cond_scale': p.cfg_scale}, disable=False, callback=self.callback_state, **extra_params_kwargs) File...

I'm running a RTX 3080 10GB, 64GB DDR5, Zen4 7950X, comfyui portable and noticed this behaviour after updating through the manager add-on in the last couple of days or so....

I was having horrendous slowdown issues with the previous portable release, sometimes with multiple minutes per iteration which made batch running impossible. However updating to the latest release v0.2.2 with...

Yeah, @LouisH99 has the answer, but use a powershell window rather than normal terminal. `mkdir audiblez` `cd audiblez` `python -m venv venv` `.\venv\Scripts\Activate.ps1` `pip install audiblez pillow wxpython` `audiblez-ui`

It might also be a torch issue if it is slow when running, in which case check the torch cuda version matches your cuda install, eg for me on CUDA...

that sounds like something is wrong with your python install - audiblez is a published package on PyPI... Try these and see if one of them fixes it: `python -m...

That sounds like your connection to pypi is blocked for some reason? Try using the direct git method? On Sun, Feb 16, 2025 at 15:39, chschmit ***@***.***(mailto:On Sun, Feb 16,...

I tinkered a bit with integrating it into audiblez, confirmed that the GPU was being used, but the performance wasn't great at ~190 characters/sec on an M4 Pro Mac Mini...

Agreed, I'm getting far better results from Hunyuan3D-2 locally than Direct3D-S2 on the HuggingFace space. Although apparently there are some improvements coming.

Try forcing pytorch to the latest nightly: `pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu126 --upgrade` Switch cu126 to whichever matches your cuda version.