level 4
明月如枫
楼主
CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 6.00 GiB of which 0 bytes is free. Of the allocated memory 5.25 GiB is allocated by PyTorch, and 122.82 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
ComfyUI Error Report
## Error Details
- **Node ID:** 22
- **Node Type:** SUPIR_Upscale
- **Exception Type:** torch.OutOfMemoryError
- **Exception Message:** CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 6.00 GiB of which 0 bytes is free. Of the allocated memory 5.25 GiB is allocated by PyTorch, and 122.82 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
## Stack Trace
然后要怎么设置?看不懂啊
2025年03月16日 08点03分
1
ComfyUI Error Report
## Error Details
- **Node ID:** 22
- **Node Type:** SUPIR_Upscale
- **Exception Type:** torch.OutOfMemoryError
- **Exception Message:** CUDA out of memory. Tried to allocate 20.00 MiB. GPU 0 has a total capacity of 6.00 GiB of which 0 bytes is free. Of the allocated memory 5.25 GiB is allocated by PyTorch, and 122.82 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
## Stack Trace
然后要怎么设置?看不懂啊