[Bug] AutoencoderKL in mmagic/models/archs.py: runwayml/stable-diffusion-v1-5 does not appear to have a file named config.json.

PancakeAwesome commented 1 year ago

Prerequisite

[X] I have searched Issues and Discussions but cannot get the expected help.
[X] I have read the FAQ documentation but cannot get the expected help.
[X] The bug has not been fixed in the latest version (main) or latest version (0.x).

Task

I'm using the official example scripts/configs for the officially supported tasks/models/datasets.

Branch

main branch https://github.com/open-mmlab/mmagic

Environment

05/23 17:43:38 - mmengine - INFO - **Environmental information** 05/23 17:43:39 - mmengine - INFO - sys.platform: linux 05/23 17:43:39 - mmengine - INFO - Python: 3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0] 05/23 17:43:39 - mmengine - INFO - CUDA available: True 05/23 17:43:39 - mmengine - INFO - numpy_random_seed: 2147483648 05/23 17:43:39 - mmengine - INFO - GPU 0,1,2: NVIDIA A100-SXM4-80GB 05/23 17:43:39 - mmengine - INFO - CUDA_HOME: /usr/local/cuda 05/23 17:43:39 - mmengine - INFO - NVCC: Cuda compilation tools, release 11.7, V11.7.99 05/23 17:43:39 - mmengine - INFO - GCC: gcc (GCC) 8.3.1 20190604 (Alibaba 8.3.1-1 2.24) 05/23 17:43:39 - mmengine - INFO - PyTorch: 2.0.0+cu117 05/23 17:43:39 - mmengine - INFO - PyTorch compiling details: PyTorch built with:

GCC 9.3
C++ Version: 201703
Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)
OpenMP 201511 (a.k.a. OpenMP 4.5)
LAPACK is enabled (usually provided by MKL)
NNPACK is enabled
CPU capability usage: AVX2
CUDA Runtime 11.7
NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86
CuDNN 8.9.1 (built against CUDA 11.8)
- Built with CuDNN 8.5
Magma 2.6.1
Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

05/23 17:43:39 - mmengine - INFO - TorchVision: 0.15.1+cu117 05/23 17:43:39 - mmengine - INFO - OpenCV: 4.7.0 05/23 17:43:39 - mmengine - INFO - MMEngine: 0.7.3 05/23 17:43:39 - mmengine - INFO - MMCV: 2.0.0 05/23 17:43:39 - mmengine - INFO - MMCV Compiler: GCC 9.3 05/23 17:43:39 - mmengine - INFO - MMCV CUDA Compiler: 11.7 05/23 17:43:39 - mmengine - INFO - MMDeploy: 1.0.0+ 05/23 17:43:39 - mmengine - INFO -

05/23 17:43:39 - mmengine - INFO - **Backend information** 05/23 17:43:39 - mmengine - INFO - tensorrt: 8.2.3.0 05/23 17:43:39 - mmengine - INFO - tensorrt custom ops: Available 05/23 17:43:39 - mmengine - INFO - ONNXRuntime: None 05/23 17:43:39 - mmengine - INFO - ONNXRuntime-gpu: 1.8.1 05/23 17:43:39 - mmengine - INFO - ONNXRuntime custom ops: NotAvailable 05/23 17:43:39 - mmengine - INFO - pplnn: None 05/23 17:43:39 - mmengine - INFO - ncnn: None 05/23 17:43:39 - mmengine - INFO - snpe: None 05/23 17:43:39 - mmengine - INFO - openvino: None 05/23 17:43:39 - mmengine - INFO - torchscript: 2.0.0 05/23 17:43:39 - mmengine - INFO - torchscript custom ops: NotAvailable 05/23 17:43:39 - mmengine - INFO - rknn-toolkit: None 05/23 17:43:39 - mmengine - INFO - rknn-toolkit2: None 05/23 17:43:39 - mmengine - INFO - ascend: None 05/23 17:43:39 - mmengine - INFO - coreml: None 05/23 17:43:39 - mmengine - INFO - tvm: None 05/23 17:43:39 - mmengine - INFO - vacc: None 05/23 17:43:39 - mmengine - INFO -

Reproduces the problem - code sample

python -c "from mmagic.apis import MMagicInferencer;sd_inferencer = MMagicInferencer(model_name='stable_diffusion')"

Reproduces the problem - command or script

python -c "from mmagic.apis import MMagicInferencer;sd_inferencer = MMagicInferencer(model_name='stable_diffusion')"

Reproduces the problem - error message

OSError: class StableDiffusion in mmagic/models/editors/stable_diffusion/stable_diffusion.py: class AutoencoderKL in mmagic/models/archs.py: runwayml/stable-diffusion-v1-5 does not appear to have a file named config.json.

Additional information

No response

Z-Fran commented 1 year ago

This is because runwayml/stable-diffusion-v1-5 hasn't been downloaded completely.

PancakeAwesome commented 1 year ago

how to download?can u tell me the link of this resource. thank u

Z-Fran commented 1 year ago

if you don't have a folder named runwayml/stable-diffusion-v1-5, it will automatically download. Or you can download it from https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main

Z-Fran commented 1 year ago

Closing due to inactivity, please reopen if there are any further problems.

PancakeAwesome commented 1 year ago

if you don't have a folder named runwayml/stable-diffusion-v1-5, it will automatically download. Or you can download it from https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main

After downloaded hug model and how can i load model from custom local path?

PancakeAwesome commented 1 year ago

@Z-Fran

LeoXing1996 commented 1 year ago

@PancakeAwesome

- stable_diffusion_v15_url = 'runwayml/stable-diffusion-v1-5'
+ stable_diffusion_v15_url = YOUR_LOCAL_PATH

unet = dict(
    type='UNet2DConditionModel',
    subfolder='unet',
    from_pretrained=stable_diffusion_v15_url)
vae = dict(
    type='AutoencoderKL',
    from_pretrained=stable_diffusion_v15_url,
    subfolder='vae')

open-mmlab / mmagic