You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Idle❌Load Session History清除
Ruyi_I2VSampler
Torch not compiled with CUDA enabled
ComfyUI Error Report
Error Details
Node ID: 19
Node Type: Ruyi_I2VSampler
Exception Type: AssertionError
Exception Message: Torch not compiled with CUDA enabled
Stack Trace
File "/home/junwei161/ComfyUI/execution.py", line 327, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/junwei161/ComfyUI/execution.py", line 202, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/junwei161/ComfyUI/execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "/home/junwei161/ComfyUI/execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/junwei161/ComfyUI/custom_nodes/Ruyi-Models/comfyui/comfyui_nodes.py", line 530, in process
pipeline.enable_sequential_cpu_offload()
File "/home/junwei161/ComfyUI/custom_nodes/Ruyi-Models/ruyi/pipeline/pipeline_ruyi_inpaint.py", line 230, in enable_sequential_cpu_offload
super().enable_sequential_cpu_offload(*args, **kwargs)
File "/root/miniconda3/envs/arc31208251_env/lib/python3.12/site-packages/diffusers/pipelines/pipeline_utils.py", line 1166, in enable_sequential_cpu_offload
cpu_offload(model, device, offload_buffers=offload_buffers)
File "/root/miniconda3/envs/arc31208251_env/lib/python3.12/site-packages/accelerate/big_modeling.py", line 198, in cpu_offload
attach_align_device_hook(
File "/root/miniconda3/envs/arc31208251_env/lib/python3.12/site-packages/accelerate/hooks.py", line 425, in attach_align_device_hook
attach_align_device_hook(
File "/root/miniconda3/envs/arc31208251_env/lib/python3.12/site-packages/accelerate/hooks.py", line 425, in attach_align_device_hook
attach_align_device_hook(
File "/root/miniconda3/envs/arc31208251_env/lib/python3.12/site-packages/accelerate/hooks.py", line 416, in attach_align_device_hook
add_hook_to_module(module, hook, append=True)
File "/root/miniconda3/envs/arc31208251_env/lib/python3.12/site-packages/accelerate/hooks.py", line 156, in add_hook_to_module
module = hook.init_hook(module)
^^^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/arc31208251_env/lib/python3.12/site-packages/accelerate/hooks.py", line 272, in init_hook
set_module_tensor_to_device(module, name, self.execution_device)
File "/root/miniconda3/envs/arc31208251_env/lib/python3.12/site-packages/accelerate/utils/modeling.py", line 339, in set_module_tensor_to_device
new_value = old_value.to(device)
^^^^^^^^^^^^^^^^^^^^
File "/root/miniconda3/envs/arc31208251_env/lib/python3.12/site-packages/torch/cuda/__init__.py", line 310, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.
{"last_node_id":33,"last_link_id":28,"nodes":[{"id":16,"type":"VHS_VideoCombine","pos":[1009.7774658203125,126.84111022949219],"size":[317,334],"flags":{},"order":6,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":13,"label":"图像"},{"name":"audio","type":"AUDIO","link":null,"shape":7,"label":"音频"},{"name":"meta_batch","type":"VHS_BatchManager","link":null,"shape":7,"label":"批次管理"},{"name":"vae","type":"VAE","link":null,"shape":7}],"outputs":[{"name":"Filenames","type":"VHS_FILENAMES","links":null,"label":"文件名"}],"properties":{"Node name for S&R":"VHS_VideoCombine"},"widgets_values":{"frame_rate":24,"loop_count":0,"filename_prefix":"Ruyi-I2V-StartEndFrames","format":"video/h264-mp4","pix_fmt":"yuv420p","crf":19,"save_metadata":true,"trim_to_audio":false,"pingpong":false,"save_output":true,"videopreview":{"hidden":false,"paused":false,"params":{"filename":"Ruyi-I2V-StartEndFrames_00001.mp4","subfolder":"","type":"output","format":"video/h264-mp4","frame_rate":24,"workflow":"Ruyi-I2V-StartEndFrames_00001.png","fullpath":"C:\\AI-video-onekey-20250117\\ComfyUI\\output\\Ruyi-I2V-StartEndFrames_00001.mp4"},"muted":false}}},{"id":24,"type":"Ruyi_TeaCache","pos":[653.2990112304688,-92.5076675415039],"size":[315,154],"flags":{},"order":4,"mode":0,"inputs":[{"name":"ruyi_model","type":"RUYI_MODEL","link":21,"label":"ruyi_model"}],"outputs":[{"name":"ruyi_model","type":"RUYI_MODEL","links":[23],"slot_index":0,"label":"ruyi_model"}],"properties":{"Node name for S&R":"Ruyi_TeaCache"},"widgets_values":[true,0.1,3,1,true]},{"id":17,"type":"LoadImage","pos":[-114.48710632324219,439.02117919921875],"size":[240.88999938964844,419.6499938964844],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[15],"slot_index":0,"label":"图像"},{"name":"MASK","type":"MASK","links":null,"label":"遮罩"}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["240321232915.png","image"]},{"id":18,"type":"LoadImage","pos":[155.7351837158203,438.60760498046875],"size":[242.10000610351562,421.6499938964844],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[16],"slot_index":0,"label":"图像"},{"name":"MASK","type":"MASK","links":null,"label":"遮罩"}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["0324202659.png","image"]},{"id":21,"type":"VHS_VideoCombine","pos":[1968.99560546875,252.7424774169922],"size":[751.6575317382812,334],"flags":{},"order":7,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":28,"label":"图像"},{"name":"audio","type":"AUDIO","link":null,"shape":7,"label":"音频"},{"name":"meta_batch","type":"VHS_BatchManager","link":null,"shape":7,"label":"批次管理"},{"name":"vae","type":"VAE","link":null,"shape":7}],"outputs":[{"name":"Filenames","type":"VHS_FILENAMES","links":null,"label":"文件名"}],"properties":{"Node name for S&R":"VHS_VideoCombine"},"widgets_values":{"frame_rate":1,"loop_count":0,"filename_prefix":"Ruyi-I2V-StartFrame","format":"video/h264-mp4","pix_fmt":"yuv420p","crf":19,"save_metadata":true,"trim_to_audio":false,"pingpong":false,"save_output":true,"videopreview":{"hidden":false,"paused":false,"params":{"filename":"Ruyi-I2V-StartFrame_00003.mp4","subfolder":"","type":"output","format":"video/h264-mp4","frame_rate":24,"workflow":"Ruyi-I2V-StartFrame_00003.png","fullpath":"C:\\AI-video-onekey-20250117\\ComfyUI\\output\\Ruyi-I2V-StartFrame_00003.mp4"},"muted":false}}},{"id":15,"type":"Ruyi_LoadModel","pos":[-72.35037231445312,-96.2402114868164],"size":[315,154],"flags":{},"order":2,"mode":0,"inputs":[],"outputs":[{"name":"ruyi_model","type":"RUYI_MODEL","links":[22],"slot_index":0,"label":"ruyi_model"}],"properties":{"Node name for S&R":"Ruyi_LoadModel"},"widgets_values":["Ruyi-Mini-7B","yes","no","none","fp8_e4m3fn"]},{"id":19,"type":"Ruyi_I2VSampler","pos":[537.3553466796875,446.34320068359375],"size":[327.5999755859375,338],"flags":{},"order":5,"mode":0,"inputs":[{"name":"ruyi_model","type":"RUYI_MODEL","link":23,"label":"ruyi_model"},{"name":"start_img","type":"IMAGE","link":15,"label":"start_img"},{"name":"end_img","type":"IMAGE","link":16,"shape":7,"label":"end_img"}],"outputs":[{"name":"images","type":"IMAGE","links":[13,28],"slot_index":0,"label":"images"}],"properties":{"Node name for S&R":"Ruyi_I2VSampler"},"widgets_values":[48,512,4971874773355,"randomize",25,7,"DDIM","auto","auto","low_memory_mode","5"]},{"id":25,"type":"Ruyi_EnhanceAVideo","pos":[303.1950988769531,-81.68051147460938],"size":[292.72698974609375,130],"flags":{},"order":3,"mode":0,"inputs":[{"name":"ruyi_model","type":"RUYI_MODEL","link":22,"label":"ruyi_model"}],"outputs":[{"name":"ruyi_model","type":"RUYI_MODEL","links":[21],"slot_index":0,"label":"ruyi_model"}],"properties":{"Node name for S&R":"Ruyi_EnhanceAVideo"},"widgets_values":[true,1,0,0]}],"links":[[13,19,0,16,0,"IMAGE"],[15,17,0,19,1,"IMAGE"],[16,18,0,19,2,"IMAGE"],[21,25,0,24,0,"RUYI_MODEL"],[22,15,0,25,0,"RUYI_MODEL"],[23,24,0,19,0,"RUYI_MODEL"],[28,19,0,21,0,"IMAGE"]],"groups":[{"id":1,"title":"B站、Youtube:T8star-Aix","bounding":[-967.9205322265625,-745.988037109375,4167.669921875,308.8702087402344],"color":"#3f789e","font_size":240,"flags":{}}],"config":{},"extra":{"ds":{"scale":0.6967877662371478,"offset":[193.06531039397726,33.60196303931741]},"node_versions":{"ComfyUI-VideoHelperSuite":"cad87a17a3ff5e03c26cf55e4dc90397b5642503","Ruyi-Models":"f6543017c973c5150f3a9072a43a4ca690fb307e","comfy-core":"unknown"},"VHS_latentpreview":false,"VHS_latentpreviewrate":0,"ue_links":[]},"version":0.4}
Additional Context
(Please add any additional context or steps to reproduce the error here)
`
The text was updated successfully, but these errors were encountered:
I think this issue arises because the code defaults to using CUDA devices.
Since I do not have access to an XPU device, it is difficult for me to replicate this scenario. Could you help us modify the code and test its feasibility on XPU? If you can help with the modifications, I think we need to:
Pass the device (might be this or something should be used for XPU) to the enable_sequential_cpu_offload method;
Change the "cuda" string to the device in pipeline_ruyi_inpaint (and possibly in other code files as well).
Let's start with these adjustments to see if they enable running on XPU. Looking forward to your response.
Hello, could you fix the support for Intel Arc XPU graphics cards?
Sampler for Image to Video,ERROR:
*-display
description: VGA compatible controller
product: DG2 [Arc A770]
vendor: Intel Corporation
physical id: 0
bus info: pci@0000:03:00.0
logical name: /dev/fb0
version: 08
width: 64 bits
clock: 33MHz
capabilities: pciexpress msi pm vga_controller bus_master cap_list rom fb
configuration: depth=32 driver=i915 latency=0 resolution=1920,1080
resources: iomemory:400-3ff irq:159 memory:81000000-81ffffff memory:4000000000-43ffffffff memory:82000000-821fffff
`
管理器
1
Idle❌Load Session History清除
Ruyi_I2VSampler
Torch not compiled with CUDA enabled
ComfyUI Error Report
Error Details
Stack Trace
System Information
Devices
Logs
Attached Workflow
Please make sure that workflow does not contain any sensitive information such as API keys or passwords.
Additional Context
(Please add any additional context or steps to reproduce the error here)
`
The text was updated successfully, but these errors were encountered: