laohsh的个人资料 - RAT

laohsh laohsh

关注数: 16 粉丝数: 4 发帖数: 146 关注贴吧数: 4

comfyui 最新版子图出问题了

使用JoyCaptionTwo时出错，请大佬们帮忙解决！在线等~~~ 使用comfyui桌面端（版本0.11）安装了JoyCaptionTwo，安装后一切正常，模型位置全对，但在运行时，他会弹出下面的错误信息：property 'device' of 'SiglipVisionTransformer' object has no setter。导致不能进行反推。下面是部分日志： D:\LLM\ComfyUI\models\clip\siglip-so400m-patch14-384 `torch_dtype` is deprecated! Use `dtype` instead! Loading weights: 100%|██████████| 888/888 [00:52<00:00, 13.43it/s, MaterializingLoading weights: 100%|██████████| 888/888 [00:52<00:00, 16.99it/s, Materializing param=vision_model.post_layernorm.weight] Loading VLM's custom vision model Requested to load SiglipVisionTransformer loaded completely; 809.17 MB loaded, full load: True !!! Exception during processing !!! property 'device' of 'SiglipVisionTransformer' object has no setter Traceback (most recent call last): File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_patcher.py", line 980, in partially_load self.load(device_to, lowvram_model_memory=current_used + extra_memory, force_patch_weights=force_patch_weights, full_load=full_load) File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_patcher.py", line 806, in load self.model.device = device_to ^^^^^^^^^^^^^^^^^ File "D:\LLM\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 2072, in __setattr__ super().__setattr__(name, value) AttributeError: property 'device' of 'SiglipVisionTransformer' object has no setter During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 518, in execute output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 329, in get_output_data return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 303, in _async_map_node_over_list await process_inputs(input_dict, i) File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\execution.py", line 291, in process_inputs result = f(**inputs) ^^^^^^^^^^^ File "D:\LLM\ComfyUI\custom_nodes\comfyui_slk_joy_caption_two\joy_caption_two_node.py", line 341, in generate vision_outputs = joy_two_pipeline.clip_model.encode_image(pixel_values) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\LLM\ComfyUI\custom_nodes\comfyui_slk_joy_caption_two\joy_caption_two_node.py", line 66, in encode_image load_models_gpu([self.patcher], force_full_load=True, force_patch_weights=True) File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_management.py", line 715, in load_models_gpu loaded_model.model_load(lowvram_model_memory, force_patch_weights=force_patch_weights) File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_management.py", line 520, in model_load self.model_use_more_vram(use_more_vram, force_patch_weights=force_patch_weights) File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_management.py", line 550, in model_use_more_vram return self.model.partially_load(self.device, extra_memory, force_patch_weights=force_patch_weights) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_patcher.py", line 982, in partially_load self.detach() File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_patcher.py", line 991, in detach self.unpatch_model(self.offload_device, unpatch_weights=unpatch_all) File "C:\Users\zhyms\AppData\Local\Programs\ComfyUI\resources\ComfyUI\comfy\model_patcher.py", line 860, in unpatch_model self.model.device = device_to ^^^^^^^^^^^^^^^^^ File "D:\LLM\ComfyUI\.venv\Lib\site-packages\torch\nn\modules\module.py", line 2072, in __setattr__ super().__setattr__(name, value) AttributeError: property 'device' of 'SiglipVisionTransformer' object has no setter Prompt executed in 66.78 seconds Error handling request from 127.0.0.1 FETCH ComfyRegistry Data [DONE] [ComfyUI-Manager] default cache updated: http://tieba.baidu.com/mo/q/checkurl?url=https%3A%2F%2Fapi.comfy.org%2Fnodes&urlrefer=8ddc292ec7c274253f56163e89975242 FETCH DATA from: D:\LLM\ComfyUI\user\__manager\cache\1514988643_custom-node-list.json [DONE] [ComfyUI-Manager] All startup tasks have been completed.

1 下一页