|
|
发表于 2026-7-20 19:34:23
|
显示全部楼层
大佬求助 我是N卡 8G
[prompt_id: 86afc00d-8441-4c72-8579-b73ca2a1c183, node_id: 164, node_type: CLIPTextEncode, executed: {"166", "356", "352", "167", "156"}, exception_message: "no kernel image is available for execution on the device\nSearch for cudaErrorNoKernelImageForDevice in https://docs.nvidia.com/cuda/cud ... _CUDART__TYPES.html for more information.\nCUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.\nFor debugging consider passing CUDA_LAUNCH_BLOCKING=1\nCompile with TORCH_USE_CUDA_DSA to enable device-side assertions.\n\ntorch.AcceleratorError", traceback: "File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\execution.py\", line 542, in execute_in_output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, objs, input_data_all, execution_block_cb, execution_block_cb, pre_execute_cb, pre_execute_cb_v3, data_v3, data_v3)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\execution.py\", line 341, in get_output_data, return_values = await asyncio_map_node_over_list(prompt_id, unique_id, objs, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, v3_data=v3_data)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\execution.py\", line 315, in asyncio_map_node_over_list, n = await process_inputs(input_dict, i, function, results)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\execution.py\", line 303, in process_inputs, result = self.func(*inputs)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\nodes.py\", line 77, in encode_n, return cliplip.encode_from_tokens(sd, tokens, pool_output=True)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\sd.py\", line 329, in encode_from_tokens, scheduled_pooled_dict = self.encode_from_tokens(return_pooled=return_pooled, return_dict=True)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\sd.py\", line 338, in encode_from_tokens, out = self.cond_stage_model.encode_token_weights(tokens)[0]\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\text_encoders\\k2.py\", line 44, in encode_token_weights, out, pooled, extra = super().encode_token_weights(token_weight_pairs)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\sd1_clip.py\", line 737, in encode_token_weights, out = getattr(self, self.clip).encode_token_weights(tokens_weight_pairs)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\sd1_clip.py\", line 45, in encode_token_weights, out = self.encode_to_embedding(tokens)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\sd1_clip.py\", line 306, in encode_to_embedding, self.encoder(tokens)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\python\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1775, in wrapped_call, return self._call_impl(*args, **kwargs)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\python\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1786, in _call_impl, return forward_call(*args, **kwargs)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\sd1_clip.py\", line 266, in forward, embeds, attention_mask, num_tokens, embeds = info.self_process_tokens(devices, device)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\text_encoders\\k2.py\", line 213, in process_tokens, embeds = self.transformer.get_input_embeddings(tokens)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\python\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1775, in wrapped_call, return self._call_impl(*args, **kwargs)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\python\\Lib\\site-packages\\torch\\nn\\modules\\module.py\", line 1786, in _call_impl, return forward_call(*args, **kwargs)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\ops.py\", line 761, in forward, return self.forward_comfy_cast_weights(*args, **kwargs)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\ops.py\", line 1460, in forward_comfy_cast_weights, return super().forward_comfy_cast_weights(input, out_dtype=out_dtype)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\ComfyUI\\comfy\\ops.py\", line 753, in forward_comfy_cast_weights, x = torch.nn.functional.embedding(input, weight, self.padding_idx, self.max_norm, self.norm_type, self.scale_grad_by_freq, self.sparse), to_dtype=output_dtype)\n\n File \"E:\\Jianxia-krea2-AI-Pack-Lite-v2.1\\python\\Lib\\site-packages\\torch\\nn\\functional.py\", line 2542, in embedding, return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)\n\nCurrent inputs: {"text": "1.东亚年轻女性,浅亚麻齐肩短发,淡黄色棉麻长裙,春日樱花林间,午后暖阳和煦阳光,丁达尔树叶光斑,清新原生皮肤,清晰毛孔,淡淡雀斑,暖光伤素影,浅褐层,浅层深,留白400HD胶片,清澈和清晰边界,低调饱和油画,画面大量留白,纤细柔和五官,平淡柔软妆,无油光反面","clip": "comfy.sd1_clip_object", "0x0000025B1C876B5C0"}}
current_outputs: {"166": "135", "356": "356", "Save_Base", "158", "161", "153", "352", "167", "357", "156", "168", "164", "140"}, timestamp: 1784546631065 |
|