Home Fast Hunyuan GGUF: 8x Faster Video Generation for ComfyUI! byAi Verse •January 19, 2025 1 Fast Hunyuan WorkflowFAST HUNYUAN GGUFclip_l.safetensorsllava_llama3Vae Facebook Twitter
Hi,
ReplyDeleteI'm getting out of memory error on DualClipLoader node
## Error Details
- **Node ID:** 11
- **Node Type:** DualCLIPLoader
- **Exception Type:** torch.OutOfMemoryError
- **Exception Message:** Allocation on device
## Stack Trace
## System Information
- **ComfyUI Version:** 0.3.12
- **Arguments:** ComfyUI\main.py --windows-standalone-build --cuda-device 0 --gpu-only
- **OS:** nt
- **Python Version:** 3.12.8 (tags/v3.12.8:2dc476b, Dec 3 2024, 19:30:04) [MSC v.1942 64 bit (AMD64)]
- **Embedded Python:** true
- **PyTorch Version:** 2.5.1+cu124
## Devices
- **Name:** cuda:0 NVIDIA GeForce RTX 4060 8GB Laptop GPU : cudaMallocAsync
- **Type:** cuda
- **VRAM Total:** 8585216000
- **VRAM Free:** 6344930380
- **Torch VRAM Total:** 7751073792
- **Torch VRAM Free:** 6344930380
## Logs
torch\nn\modules\linear.py", line 106, in __init__
torch.empty((out_features, in_features), **factory_kwargs)
torch.OutOfMemoryError: Allocation on device