Jimmy Andersson

Thank you, you are very helpful as usual, I switched to real mode and `with torch.inference_mode():`, and it works great. Everything seems faster with `with torch.inference_mode():` also, maybe I'm wrong....

I noticed the workflow was not embedded in the resulting images when using real mode, is that a bug?

Not relevant to ComfyScript but.. I made a custom node that unloads unused models, but it's not working, is this because ComfyUI uses tail end recursion method? 

With 4 checkpoints loaded the ksampler is incredible slow 20 seconds per iteration and sometimes crash the computer compared to 5 iteration per second with 3 checkpoints loaded.

I got good speed with 4 checkpoints using my script with `unload_model_clones(model)` in real mode, but no metadata in the image is a problem and I'm searching for the easiest...

I updated, error now if `import torch` before ``` from comfy_script.runtime.real import * load() from comfy_script.runtime.real.nodes import * ``` Probably related to http://github.com/pytorch/pytorch/issues/104801 No issue for me, but I thought...

> I got good speed with 4 checkpoints using my script with unload_model_clones(model) in real mode I take that back, I still have problems, when RAM usage reaches 100% my...

Thank you for your help, I was unclear, the workflow is not loaded when I drag and drop the webp file, but It is loaded with a png file, with...

It was merged and I updated ComfyUI, checked app.js for the change. Still does not work. Can't upload webp to github, so here is link https://drive.google.com/file/d/1IxlsA5OMxaHD0f3sYbrwExV-hxhMDqWl/view?usp=sharing The embedding looks a...

Ok thank you.