Yvggeniy Romanskiy

I can see the logic in your what you suggesting but its not the case in this instance. As you suggested I tried to change "**Maximum prompt size in tokens**"...

Ok I did some more searching and experimentation and found that if I add **--pre_layer 34** flag it resolve my OOM issue but it makes it very slow, if I...

Yes, looks like changing he **Maximum prompt size in tokens** slider helps with the OOM now, I don't know yet if this fix the issue or just allows for some...

same exact issue, it started after the latest update I think. ``` Replace CrossAttention.forward to use xformers caching latents. 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 498/498 [00:29

I was just looking into how I can load custom YOLOv8 model. +1 on this request this tool can become very powerful if you can load custom modules you trained...

You can setup a negative prompt to disallow certain things

You need to download them manually from https://huggingface.co/camenduru/YoloWorld-EfficientSAM/tree/main efficient_sam_s_cpu.jit efficient_sam_s_gpu.jit And put them in the `custom_nodes\ComfyUI-YoloWorld-EfficientSAM` directory This whole plugin looks super sketchy, everything is hard coded and using outdated...

> Will it be possible to use kohya to train Stable Diffusion 3 LoRAs? +1

I'm having the same issue, I'm running this on Arch Linux in a container, specifically CachyOS if this makes any difference. It was working fine on windows11 when I was...

@Nynxz Thank you! Can confirm, running perfectly without any OOM issues! I'm running it inside a docker container form the git repo, all I did is to change one line...