== CUDA ==
CUDA Version 13.1.1
comfyui.logs.launch_cli_args {"args":"--disable-xformers --disable-smart-memory --disable-cuda-malloc --disable-dynamic-vram --front-end-version Comfy-Org/ComfyUI_frontend@v1.58.0"}
[ComfyUI] [INFO] ComfyUI CLI_ARGS from environment: --disable-xformers --disable-smart-memory --disable-cuda-malloc --disable-dynamic-vram --front-end-version Comfy-Org/ComfyUI_frontend@v1.58.0
** Python version:
[ComfyUI-Error] [1m[31m[ERROR][0m [ComfyUI-Manager] PyTorch is not installed
[ComfyUI-Error] error: externally-managed-environment
[ComfyUI-Error] [1m[33m[WARNING][0m WARNING: You need pytorch with cu130 or higher to use optimized CUDA operations.
If you are on nvidia 20 series and above it is required that you update your pytorch to cu130 or higher.
[32m[INFO][0m Found comfy_kitchen backend cuda: {'available': True, 'disabled': True, 'unavailable_reason': None, 'capabilities': ['adaln', 'apply_rope', 'apply_rope1', 'apply_rope1_', 'apply_rope_', 'apply_rope_split_half', 'apply_rope_split_half1', 'apply_rope_split_half1_', 'apply_rope_split_half_', 'closest_point_on_mesh', 'connected_components', 'convrot_w4a4_linear', 'delaunay3d', 'dequantize_convrot_w4a4_weight', 'dequantize_int8_convrot_weight', 'dequantize_int8_convrot_weight_dtype', 'dequantize_int8_simple', 'dequantize_int8_simple_dtype', 'dequantize_nvfp4', 'dequantize_per_tensor_fp8', 'dequantize_w4a8_int8_weight', 'edge_collapse_checks', 'fp16_conv3d', 'fp16_conv3d_out', 'fp16_linear', 'gemv_awq_w4a16', 'group_norm_silu_pad3d', 'group_norm_silu_pad3d_out', 'int8_linear', 'mesh_bvh', 'min_cut', 'na3d', 'prepare_int4_weight_for_int8_linear', 'quantize_and_rotate_rowwise', 'quantize_convrot_w4a4_weight', 'quantize_int8_convrot_weight', 'quantize_int8_rowwise', 'quantize_int8_tensorwise', 'quantize_mxfp8', 'quantize_nvfp4', 'quantize_per_tensor_fp8', 'quantize_svdquant_w4a4', 'quantize_w4a8_int8_weight', 'rms_adaln', 'rms_rope', 'rms_rope1', 'rms_rope1_', 'rms_rope_', 'rms_rope_split_half', 'rms_rope_split_half1', 'rms_rope_split_half1_', 'rms_rope_split_half_', 'rotate_int8_convrot_weight', 'scaled_mm_nvfp4', 'scaled_mm_svdquant_w4a4', 'sol_attn', 'stochastic_rounding_fp8', 'w4a8_int8_linear', 'w4a8_packed_linear']}
[32m[INFO][0m Found comfy_kitchen backend hip: {'available': False, 'disabled': False, 'unavailable_reason': 'PyTorch ROCm/HIP runtime not available', 'capabilities': []}
[32m[INFO][0m pytorch version: 2.11.0+cu128
[ComfyUI-Error] [32m[INFO][0m Device: cuda:0 NVIDIA GB10 : native
[ComfyUI-Error] [32m[INFO][0m Using pytorch attention
[ComfyUI-Error] [32m[INFO][0m Python version: 3.12.3 (main, Aug 31 2026, 10:18:26) [GCC 13.3.0]
[ComfyUI-Error] [32m[INFO][0m ComfyUI version: 0.42.1
ModuleNotFoundError: No module named 'numexpr'
ModuleNotFoundError: No module named 'cv2'
ModuleNotFoundError: No module named 'cv2'
ModuleNotFoundError: No module named 'cv2'
ModuleNotFoundError: No module named 'cv2'
ModuleNotFoundError: No module named 'cv2'
ModuleNotFoundError: No module named 'segment_anything'
ModuleNotFoundError: No module named 'cv2'
(pysssss:WD14Tagger) [DEBUG] Using ORT providers: CUDAExecutionProvider, CPUExecutionProvider
ModuleNotFoundError: No module named 'insightface'
ModuleNotFoundError: No module named 'deepdiff'
ModuleNotFoundError: No module named 'cv2'
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/ComfyUI-Impact-Pack
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/comfyui_controlnet_aux
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/comfyui_segment_anything
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/ComfyUI-Crystools
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/PuLID_ComfyUI
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/ComfyUI-Impact-Subpack
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/ComfyUI_InstantID
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/ComfyUI-layerdiffuse
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/ComfyUI_FaceAnalysis
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/ComfyUI_FizzNodes
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/ComfyUI-Inspire-Pack
[ComfyUI-Error] [32m[INFO][0m    0.0 seconds (IMPORT FAILED): /root/ComfyUI/custom_nodes/ComfyUI-VideoHelperSuite
[ComfyUI-Error] [32m[INFO][0m Using pytorch attention in VAE
[ComfyUI-Error] [32m[INFO][0m Using pytorch attention in VAE
[ComfyUI-Error] [32m[INFO][0m VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
[ComfyUI-Error] [32m[INFO][0m CLIP/text encoder model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
[ComfyUI-Error] [32m[INFO][0m loaded completely; 21135.38 MB usable, 235.84 MB loaded, full load: True
[ComfyUI-Error] [32m[INFO][0m loaded completely; 21117.50 MB usable, 1639.41 MB loaded, full load: True
[ComfyUI-Error] 100%|██████████| 20/20 [00:03<00:00,  8.18it/s]
[ComfyUI-Error] 100%|██████████| 20/20 [00:03<00:00,  6.15it/s]
[ComfyUI-Error] [32m[INFO][0m loaded completely; 20847.69 MB usable, 159.56 MB loaded, full load: True
[ComfyUI-Error] [32m[INFO][0m [32mPrompt executed in 9.41 seconds[0m
