Files
li-lizhe 2176b74083 Add 'auto' device option to nodes with hardcoded CUDA/CPU device lists
Several nodes only exposed a 'cuda'/'cpu' device dropdown, forcing users on
any other ComfyUI-supported accelerator (Ascend NPU, XPU, MPS) to run on CPU
even when their device is available.

Add a shared DEVICE_LIST_OPTIONS constant and get_device() helper in
imagefunc.py that resolve 'auto' to ComfyUI's default device, and use them in
the VITMatte-based matting nodes and the VQA model loader so non-CUDA devices
can be selected from the UI.
2026-09-16 10:08:47 +08:00
..
2024-12-15 18:16:27 +08:00
2024-12-19 19:17:46 +08:00
2026-01-11 12:52:41 +08:00
2024-12-16 16:40:17 +08:00
2024-12-15 10:19:51 +08:00
2024-12-15 10:19:51 +08:00
2024-12-11 23:40:28 +08:00
2025-03-26 11:39:50 +08:00
2024-12-19 19:17:46 +08:00
2025-02-13 13:07:10 +08:00
2024-12-06 00:09:12 +08:00
2024-12-05 17:53:25 +08:00
2024-12-05 18:58:38 +08:00