Markus Hartung

Alright, if it is by design I guess we can close this issue. However, it would be nice if it was clear in the documentation that this is the behavior.

ComfyUI should perhaps have their own text-node because this one doesn't consistently show the generated text. See the linked issue

> Hi @hartmark, thank you for providing the steps to reproduce. We will try to reproduce the issue internally and investigate it from there. Cool, just poke me if you...

I have noticed that this is also a certain way to reproduce the issue: https://github.com/ROCm/ROCm/issues/2196#issuecomment-2295441030

I saw that ROCm 6.2 python torch libraries have been released so I have updated my docker-compose.repo. I also may have found a workaround for the lockups, ComfyUI released a...

I may have been to quick to hope for success. After the KSampler step completed it was on "VAE decode" for ages and after a while I got a lockup...

I have tested some more and it seems that ComfyUI just gets out of memory now and doesn't try to use system ram to continue. I have tried using --lowvram...

It seems I still have problems where my whole computer locks up, not even altgr-rei can make me recover and there's nothing in the kernel log.

> Hi @hartmark , Thank you for your patience. For the past few days, we've been attempting to reproduce this issue with various configurations. Just an update that we are...

> The `--no-half-vae` flag is for the webui. So in this case, it is added to your startup-webui.sh file: `python3 launch.py --skip-python-version-check --enable-insecure-extension-access --listen --port 81 --api --precision full --no-half...