FLUX.1 INPAINTING
V3.0:
Original：
input2: Use the segmentanything model to segment the mask according to the prompt (keep the details);
input3: Use the segmentanything model to segment the mask according to the prompt (completely replace);
V2.0:
Added the ability to use the character Lora to fix images
Description
FAQ
Comments (2)
the workflow maybe good... whatever happend. it destroyed my cuda/onnx enviroment while getting the nodes
D:\a\_work\1\s\onnxruntime\python\onnxruntime_pybind_state.cc:636 onnxruntime::python::CreateExecutionProviderInstance CUDA_PATH is set but CUDA wasn't able to be loaded. Please install the correct version of CUDA and cuDNN as mentioned in the GPU requirements page (https://onnxruntime.ai/docs/execution-providers/CUDA-ExecutionProvider.html#requirements), make sure they're in the PATH, and that your GPU is supported
I do not have a D: partition and those folders
I would also like to understand what this workflow does because it seems to me that it does not work. I mean, I do not understand where one should put one's hand to apply the changes, because the only thing I have seen is that during the installation phase, it uninstalls a lot of stuff and reinstalls other versions, plus other things that I have not had time to see. So I wonder: is it safe to install this workflow? What exactly do the added nodes do?