ComfyUI InstantID Error

[xiecon]

Your environment

OS

Linux

OneDiff git commit id

500459f7c0d02d177efad5c898f44c6cf518d0d1

OneFlow version info

Run python -m oneflow --doctor and paste it here. path: ['/opt/conda/lib/python3.10/site-packages/oneflow'] version: 0.9.1.dev20240308+cu118 git_commit: 88ece9e cmake_build_type: Release rdma: True mlir: True enterprise: False

How To Reproduce

Steps to reproduce the behavior(code or script): 启动ComfyUI：python main.py 按照教程按照环境：https://github.com/siliconflow/onediff/blob/main/onediff_comfy_nodes/workflows/ComfyUI_InstantID_OneDiff.md load以上链接里的流程图

The complete error message

W20240311 13:16:28.580902 1556 cuda_stream.cpp:49] Runtime version 8.7 of cuDNN incompatible with compiletime version 8.9. ERROR run got error: <class 'oneflow._oneflow_internal.exception.Exception'> Cannot find the kernel matching Current OperatorConf. The Info of OperatorConf are op_name: model.text_model.encoder.layers.1.self_attn-softmax-62 op_type_name: softmax DeviceType_Name: kCPU DataType_Name of in_0: kFloat16 DataType_Name of out_0: kFloat16 File "oneflow/core/job/job_interpreter.cpp", line 312, in InterpretJob RunNormalOp(launch_context, launch_op, inputs) File "oneflow/core/job/job_interpreter.cpp", line 224, in RunNormalOp it.Apply(op, inputs, &outputs, OpExprInterpContext(empty_attr_map, JUST(launch_op.device))) File "oneflow/core/framework/op_interpreter/eager_local_op_interpreter.cpp", line 155, in NaiveInterpret PhysicalRun([&](InstructionsBuilder builder) -> Maybe ... output_eager_blob_objects), ctx, result->stream()); }) File "oneflow/core/framework/instructions_builder.h", line 168, in PhysicalRun Build(&instructions_builder) File "oneflow/core/framework/instructions_builder.cpp", line 400, in Call vm::OpCallInstructionPolicy::New( vm_stream, opkernel ... global_tensor_infer_result, ctx, one::CurrentDevVmDepObjectConsumeMode()) File "oneflow/core/vm/op_call_instruction_policy.h", line 50, in New ptr->Init() File "oneflow/user/kernels/stateful_opkernel.cpp", line 920, in ChooseOpKernel user_op::UserOpRegistryMgr::Get().GetOpKernelRegistryResult(op_type_name, reg_ctx) Error Type: oneflow.ErrorProto.op_kernel_not_found_error Exception in call: e=Exception('Cannot find the kernel matching Current OperatorConf. The Info of OperatorConf are \n op_name: model.text_model.encoder.layers.1.self_attn-softmax-62\n op_type_name: softmax\n DeviceType_Name: kCPU\n DataType_Name of in_0: kFloat16\n DataType_Name of out_0: kFloat16\n File "oneflow/core/job/job_interpreter.cpp", line 312, in InterpretJob\n RunNormalOp(launch_context, launch_op, inputs)\n File "oneflow/core/job/job_interpreter.cpp", line 224, in RunNormalOp\n it.Apply(op, inputs, &outputs, OpExprInterpContext(empty_attr_map, JUST(launch_op.device)))\n File "oneflow/core/framework/op_interpreter/eager_local_op_interpreter.cpp", line 155, in NaiveInterpret\n PhysicalRun([&](InstructionsBuilder builder) -> Maybe ... output_eager_blob_objects), ctx, result->stream()); })\n File "oneflow/core/framework/instructions_builder.h", line 168, in PhysicalRun\n Build(&instructions_builder)\n File "oneflow/core/framework/instructions_builder.cpp", line 400, in Call\n vm::OpCallInstructionPolicy::New( vm_stream, opkernel ... global_tensor_infer_result, ctx, one::CurrentDevVmDepObjectConsumeMode())\n File "oneflow/core/vm/op_call_instruction_policy.h", line 50, in New\n ptr->Init()\n File "oneflow/user/kernels/stateful_opkernel.cpp", line 920, in ChooseOpKernel\n user_op::UserOpRegistryMgr::Get().GetOpKernelRegistryResult(op_type_name, reg_ctx)\nError Type: oneflow.ErrorProto.op_kernel_not_found_error')

[strint]

We have fixed this in oneflow. And the new oneflow version is on the way.

[xiecon]

请问有预期发布新版本的时间点吗？

[strint]

请问有预期发布新版本的时间点吗？

我检查下哈，按说今天可以

[strint]

正在编译发布，好了我 at 你 @xiecon

[strint]

@xiecon

已经发布，请更新 oneflow 到最新版本：https://github.com/siliconflow/onediff?tab=readme-ov-file#1-install-oneflow

[xiecon]

非常感谢