Enable depth option in ControlNet Choose the appropriate depth model as postprocessor ( diffusion_pytorch_model.safetensors) Do not choose preprocessor Try to generate image with SDXL1.0 base model What should have happened? It should have launched the depth model Commit where the problem happens...
(0), and kernel assert is disabled: ``` python setup.py develop ``` Verify CMakeCache.txt has correct value. ``` /xxxx/pytorch/build$ grep USE_ROCM_KERNEL_ASSERT CMakeCache.txt USE_ROCM_KERNEL_ASSERT:BOOL=0 ``` Tested the following code in ROCm build and CUDA build, and expected...
Disabling' pytorch和cuda cudnn都重装了好几次了 分享21 守望先锋游戏吧 施瓦辛格康熙✨ 纠结。。A卡驱动问题OverWatch? may experience a random or intermittent hang on some system configurations. Disabling Radeon ReLive as a temporary workaround may resolve the issue. 我就没开 ReLive还是不管用啊!
cuda12.1-py3.10-gcc9-sm86 / test (inductor_cpp_wrapper, 1, 1, linux.g5.4xlarge.nvidia.gpu) Node.js 16 actions are deprecated. Please update the following actions to use Node.js 20: pytorch/test-infra/.github/actions/setup-ssh@main, malfet/checkout@silent-checkout, nick-fields/retry...