RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument mat2 in method wrapper_CUDA_mm) #47
Comments
|
Could you please share your workflow? |
|
|
新建_文本文档_(2).json |
|
Afterwards, I still report the same mistakes |
|
2024-12-03T10:59:55.886986 - 2024-12-03T10:59:56.120359 - Prompt executed in 17.13 seconds 2024-12-03T11:00:01.247215 - Prompt executed in 0.49 seconds 2024-12-03T11:00:03.196133 - Prompt executed in 0.18 seconds {"last_node_id":93,"last_link_id":139,"nodes":[{"id":89,"type":"KSampler","pos":[5022,746],"size":[315,262],"flags":{},"order":9,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":133,"label":"模型"},{"name":"positive","type":"CONDITIONING","link":132,"label":"正面条件"},{"name":"negative","type":"CONDITIONING","link":136,"label":"负面条件"},{"name":"latent_image","type":"LATENT","link":139,"label":"Latent"}],"outputs":[{"name":"LATENT","type":"LATENT","links":[134],"slot_index":0,"label":"Latent"}],"properties":{"Node name for S&R":"KSampler"},"widgets_values":[835765754753103,"randomize",20,1,"euler","normal",1]},{"id":12,"type":"UNETLoader","pos":[3867,1117],"size":[315,82],"flags":{},"order":0,"mode":0,"inputs":[],"outputs":[{"name":"MODEL","type":"MODEL","links":[114],"slot_index":0,"shape":3,"label":"模型"}],"properties":{"Node name for S&R":"UNETLoader"},"widgets_values":["flux_dev.safetensors","fp8_e4m3fn"]},{"id":11,"type":"DualCLIPLoader","pos":[3824,1290],"size":[315,106],"flags":{},"order":1,"mode":0,"inputs":[],"outputs":[{"name":"CLIP","type":"CLIP","links":[127,137],"slot_index":0,"shape":3,"label":"CLIP"}],"properties":{"Node name for S&R":"DualCLIPLoader"},"widgets_values":["clip_l.safetensors","t5xxl_fp16.safetensors","flux"]},{"id":10,"type":"VAELoader","pos":[4216,883],"size":[315,58],"flags":{},"order":2,"mode":0,"inputs":[],"outputs":[{"name":"VAE","type":"VAE","links":[12],"slot_index":0,"shape":3}],"properties":{"Node name for S&R":"VAELoader"},"widgets_values":["ae.safetensors"]},{"id":93,"type":"EmptyLatentImage","pos":[4706,1383],"size":[315,106],"flags":{},"order":3,"mode":0,"inputs":[],"outputs":[{"name":"LATENT","type":"LATENT","links":[139],"label":"Latent"}],"properties":{"Node name for S&R":"EmptyLatentImage"},"widgets_values":[1024,1024,1]},{"id":8,"type":"VAEDecode","pos":[5036,1235],"size":[237.8846435546875,89.71307373046875],"flags":{"collapsed":false},"order":10,"mode":0,"inputs":[{"name":"samples","type":"LATENT","link":134,"label":"Latent"},{"name":"vae","type":"VAE","link":12,"label":"VAE"}],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[9],"slot_index":0,"label":"图像"}],"properties":{"Node name for S&R":"VAEDecode"},"widgets_values":[]},{"id":78,"type":"IPAdapterFluxLoader","pos":[4177,681],"size":[315,106],"flags":{},"order":4,"mode":0,"inputs":[],"outputs":[{"name":"ipadapterFlux","type":"IP_ADAPTER_FLUX_INSTANTX","links":[113],"slot_index":0,"label":"ipadapterFlux"}],"properties":{"Node name for S&R":"IPAdapterFluxLoader"},"widgets_values":["ip-adapter.bin","google/siglip-so400m-patch14-384","cuda"]},{"id":90,"type":"CLIPTextEncode","pos":[4277,1304],"size":[400,200],"flags":{},"order":7,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":137,"label":"CLIP"}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[136],"label":"条件"}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":[""]},{"id":79,"type":"ApplyIPAdapterFlux","pos":[4554,662],"size":[327.5999755859375,146],"flags":{},"order":8,"mode":0,"inputs":[{"name":"model","type":"MODEL","link":114,"label":"model"},{"name":"ipadapter_flux","type":"IP_ADAPTER_FLUX_INSTANTX","link":113,"label":"ipadapter_flux"},{"name":"image","type":"IMAGE","link":116,"label":"image"}],"outputs":[{"name":"MODEL","type":"MODEL","links":[133],"slot_index":0,"label":"MODEL"}],"properties":{"Node name for S&R":"ApplyIPAdapterFlux"},"widgets_values":[0.75,0,1]},{"id":9,"type":"SaveImage","pos":[5488,577],"size":[1023.5243530273438,1062.5860595703125],"flags":{},"order":11,"mode":0,"inputs":[{"name":"images","type":"IMAGE","link":9,"label":"图像"}],"outputs":[],"properties":{"Node name for S&R":"SaveImage"},"widgets_values":["Flux_Lora"]},{"id":87,"type":"CLIPTextEncode","pos":[4260,1049],"size":[400,200],"flags":{},"order":6,"mode":0,"inputs":[{"name":"clip","type":"CLIP","link":127,"label":"CLIP"}],"outputs":[{"name":"CONDITIONING","type":"CONDITIONING","links":[132],"slot_index":0,"label":"条件"}],"properties":{"Node name for S&R":"CLIPTextEncode"},"widgets_values":["pillow"]},{"id":80,"type":"LoadImage","pos":[4553,288],"size":[315,314],"flags":{},"order":5,"mode":0,"inputs":[],"outputs":[{"name":"IMAGE","type":"IMAGE","links":[116],"slot_index":0,"label":"图像"},{"name":"MASK","type":"MASK","links":null,"label":"遮罩"}],"properties":{"Node name for S&R":"LoadImage"},"widgets_values":["flux_dev_example.png","image"]}],"links":[[9,8,0,9,0,"IMAGE"],[12,10,0,8,1,"VAE"],[113,78,0,79,1,"IP_ADAPTER_FLUX_INSTANTX"],[114,12,0,79,0,"MODEL"],[116,80,0,79,2,"IMAGE"],[127,11,0,87,0,"CLIP"],[132,87,0,89,1,"CONDITIONING"],[133,79,0,89,0,"MODEL"],[134,89,0,8,0,"LATENT"],[136,90,0,89,2,"CONDITIONING"],[137,11,0,90,0,"CLIP"],[139,93,0,89,3,"LATENT"]],"groups":[],"config":{},"extra":{"ds":{"scale":0.7972024500000012,"offset":[-3350.003932817133,-266.37604920487615]},"0246.VERSION":[0,0,4]},"version":0.4} |
It seems you have used cuda as ipadapter and clip_vision device and runs with ComfyUI windows portable. The CUDA settings might have failed, or the model has been dumped to the CPU. We will have a test on ComfyUI windows portable. |
Yes, I use ComfyUI windows portable |
|
THIS CONTINUES TO HAPPEN REGARDLESS OF SWITCHING TO GPU OR CPU, RUNS FINE WHEN U SWITCH TO GPU AND IT WILL GIVE U AN ERROR AFTER ONE RUN, SO U SWITCH TO CPU, AGAIN IT GENERATES AN IMAGE, JUST ONE AND BAM !!! U WILL GET THIS ERROR YET AGAIN. P.S IT'S NOT THE CASE ONLY ON THE PORTABLE, BEFORE THIS I HAD DONE A STANDALONE INSTALLATION OF COMFYUI AND I WOULD GET THE SAME ERROR, SO IT'S GOT NOTHING AT ALL TO DO WITH THE PORTABLE VERSION. THIS STARTED EXACTLY AFTER THE LAST UPDATE OF PULID, I'VE POSTED ABOUT THIS SEVERAL TIMES AND ON THE COMFYUI DISCORD AS WELL BUT NO ONE SEEMS TO HAVE A SOLUTION FOR IT. SOME SPOKE OF DOWNGRADING COMFY BUT THAT DIDN'T WORK EITHER. |
|
Any workarounds yet? Also found it unsolved here: comfyanonymous/ComfyUI#5763 ComfyUI Error ReportError Details
Stack TraceSystem Information
Devices
LogsWorkflow |
|
Any news on this? It was fine before the update. |
|
I have the same problem with ComfyUI on Archlinux |
|
Try this in case you are also using PuLID Flux Enhanced sipie800/ComfyUI-PuLID-Flux-Enhanced#54 |
comfyanonymous/ComfyUI#5862 (comment)
The text was updated successfully, but these errors were encountered: