6 Comments
User's avatar
Neural Foundry's avatar

Huge win for AMD users who've been stuck with suboptimal performance! The automatic ROCm selection during installtion is a nice touch since manually configuring GPU backends can be a pain. I'm curious how this compares to DirectML perfomance on the same hardware, since that was the previous workaround. The cross-attention flag support in 7.1.1 should help a lot with memory-intensive workflows.

Expand full comment
Jedrzej Kosinski's avatar

Should be a night-and-day performance improvement with ROCm vs DirectML. With DirectML, I had a W7800 go toe-to-toe with a GTX 1060 (not a typo) on Windows. You should get close to a 10x performance boost, at least.

Expand full comment
kai's avatar
2dEdited

A huge thank you for providing such a great tool!

I’ve been running some initial tests on my system, and it’s working very smoothly and perfectly stable with Python 3.12.11.

As a side note : I noticed a significant performance boost when running it on my manual ComfyUI setup with Python 3.13.9. I don't know if it is just the Python version.

in seconds

Py3.13.9 Py3.12.11 #1...Py3.12.11 #2

1........89,43.........317,63.............176,56

2........87,9...........211,21............223,56

3........88,53..........201,74.............318,05

4........84,86.........189,76.............219,25

AVG..87,6975.....230,085...........239,39

%.......100,00 .....262,36.............272,97 %

system:

Win 11

AMD Ryzen 5 7500F 6-Core Processor

AMD Radeon RX 7800 XT

64GB RAM.

test workflow:

https://openart.ai/workflows/aura_111_111/fantasy-elf-sdxl-cinematic-nsfwsfw-portrait-workflow-hires-fix-vae-ksampler-workflow/JiDA2LC9sKQnvBUbNFRQ

Expand full comment
Niinu1337's avatar

I vaguely remember the comfyui README saying somewhere that some dependencies don't support py3.13 yet so py3.12 was recommended, is this still the case or does it work with no issues already?

Expand full comment
kai's avatar

I guess there's no "no issues" option for AMD users yet. For example, I haven't tested the above version for training yet (Flux FP16/BF16), but I have a lot of trouble with my py3.13.

Expand full comment
Nhathoangfoto's avatar

Please support NVFP4 Models

Expand full comment