AMD RX 580 help?

[Herbxlicious]

Custom Node Testing

• [x] I have tried disabling custom nodes and the issue persists (see how to disable custom nodes if you need help)

Your question

i assume the rocm isn't available for the card and i'll have to run directml?

.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build [START] Security scan [DONE] Security scan

ComfyUI-Manager: installing dependencies done.

** ComfyUI startup time: 2025-12-03 11:29:16.473 ** Platform: Windows ** Python version: 3.12.10 (tags/v3.12.10:0cc8128, Apr 8 2025, 12:21:36) [MSC v.1943 64 bit (AMD64)] ** Python executable: C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\python_embeded\python.exe ** ComfyUI Path: C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI ** ComfyUI Base Folder Path: C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI ** User directory: C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\user ** ComfyUI-Manager config path: C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\user__manager\config.ini ** Log path: C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\user\comfyui.log

Prestartup times for custom nodes: 0.0 seconds: C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\custom_nodes\rgthree-comfy 0.0 seconds: C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Easy-Use 4.0 seconds: C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager

[WARNING] failed to run amdgpu-arch: binary not found. Checkpoint files will always be loaded safely. Traceback (most recent call last): File "C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\main.py", line 149, in import execution File "C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\execution.py", line 15, in import comfy.model_management File "C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 238, in total_vram = get_total_memory(get_torch_device()) / (1024 * 1024) ^^^^^^^^^^^^^^^^^^ File "C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\ComfyUI\comfy\model_management.py", line 188, in get_torch_device return torch.device(torch.cuda.current_device()) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda_init_.py", line 1069, in current_device lazy_init() File "C:\Coding\ComfyUI_windows_portable_amd\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\cuda_init.py", line 410, in _lazy_init torch._C._cuda_init() RuntimeError: No HIP GPUs are available

Logs

Other

No response

[LukeG89]

You should try this ComfyUI version, I see there are installation instructions for old cards: https://github.com/patientx/ComfyUI-Zluda

[gsxgmpkt9020]

The value of time wasted on APU can let me buy a brandly new best N card