Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' of https://github.com/corajr/stable-diffusion into corajr-main

Browse Source
This commit is contained in:
Lincoln Stein
2022-09-01 10:25:43 -04:00
parent c5e95adb49 2455bb38a4
commit a52870684a
3 changed files with 71 additions and 57 deletions
Download Patch File Download Diff File Expand all files Collapse all files

55
README-Mac-MPS.md
View File

@ -12,8 +12,7 @@ issue](https://github.com/CompVis/stable-diffusion/issues/25), and generally on
You have to have macOS 12.3 Monterey or later. Anything earlier than that won't work. You have to have macOS 12.3 Monterey or later. Anything earlier than that won't work.
BTW, I haven't tested any of this on Intel Macs but I have read that one person Tested on a 2022 Macbook M2 Air with 10-core GPU and 24 GB unified memory.
got it to work.
How to: How to:
@ -22,24 +21,23 @@ git clone https://github.com/lstein/stable-diffusion.git
cd stable-diffusion cd stable-diffusion
mkdir -p models/ldm/stable-diffusion-v1/ mkdir -p models/ldm/stable-diffusion-v1/
ln -s /path/to/ckpt/sd-v1-1.ckpt models/ldm/stable-diffusion-v1/model.ckpt PATH_TO_CKPT="$HOME/Documents/stable-diffusion-v-1-4-original" # or wherever yours is.
ln -s "$PATH_TO_CKPT/sd-v1-4.ckpt" models/ldm/stable-diffusion-v1/model.ckpt
conda env create -f environment-mac.yaml CONDA_SUBDIR=osx-arm64 conda env create -f environment-mac.yaml
conda activate ldm conda activate ldm
python scripts/preload_models.py python scripts/preload_models.py
python scripts/orig_scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms python scripts/dream.py --full_precision # half-precision requires autocast and won't work
``` ```
We have not gotten lstein's dream.py to work yet. After you follow all the instructions and run dream.py you might get several errors. Here's the errors I've seen and found solutions for.
After you follow all the instructions and run txt2img.py you might get several errors. Here's the errors I've seen and found solutions for.
### Is it slow? ### Is it slow?
Be sure to specify 1 sample and 1 iteration. Be sure to specify 1 sample and 1 iteration.
python ./scripts/txt2img.py --prompt "ocean" --ddim_steps 5 --n_samples 1 --n_iter 1 python ./scripts/orig_scripts/txt2img.py --prompt "ocean" --ddim_steps 5 --n_samples 1 --n_iter 1
### Doesn't work anymore? ### Doesn't work anymore?
@ -94,10 +92,6 @@ get quick feedback.
python ./scripts/txt2img.py --prompt "ocean" --ddim_steps 5 --n_samples 1 --n_iter 1 python ./scripts/txt2img.py --prompt "ocean" --ddim_steps 5 --n_samples 1 --n_iter 1
### MAC: torch._C' has no attribute '_cuda_resetPeakMemoryStats' #234
We haven't fixed gotten dream.py to work on Mac yet.
### OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'... ### OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'...
python scripts/preload_models.py python scripts/preload_models.py
@ -108,7 +102,7 @@ Example error.
``` ```
... ...
NotImplementedError: The operator 'aten::index.Tensor' is not current implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on [https://github.com/pytorch/pytorch/issues/77764](https://github.com/pytorch/pytorch/issues/77764). As a temporary fix, you can set the environment variable `PYTORCH_ENABLE_MPS_FALLBACK=1` to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS. NotImplementedError: The operator 'aten::_index_put_impl_' is not current implemented for the MPS device. If you want this op to be added in priority during the prototype phase of this feature, please comment on [https://github.com/pytorch/pytorch/issues/77764](https://github.com/pytorch/pytorch/issues/77764). As a temporary fix, you can set the environment variable `PYTORCH_ENABLE_MPS_FALLBACK=1` to use the CPU as a fallback for this op. WARNING: this will be slower than running natively on MPS.
``` ```
The lstein branch includes this fix in [environment-mac.yaml](https://github.com/lstein/stable-diffusion/blob/main/environment-mac.yaml). The lstein branch includes this fix in [environment-mac.yaml](https://github.com/lstein/stable-diffusion/blob/main/environment-mac.yaml).
@ -137,27 +131,18 @@ still working on it.
OMP: Error #15: Initializing libiomp5.dylib, but found libomp.dylib already initialized. OMP: Error #15: Initializing libiomp5.dylib, but found libomp.dylib already initialized.
There are several things you can do. First, you could use something You are likely using an Intel package by mistake. Be sure to run conda with
besides Anaconda like miniforge. I read a lot of things online telling the environment variable `CONDA_SUBDIR=osx-arm64`, like so:
people to use something else, but I am stuck with Anaconda for other
reasons.
Or you can try this. `CONDA_SUBDIR=osx-arm64 conda install ...`
export KMP_DUPLICATE_LIB_OK=True This error happens with Anaconda on Macs when the Intel-only `mkl` is pulled in by
a dependency. [nomkl](https://stackoverflow.com/questions/66224879/what-is-the-nomkl-python-package-used-for)
is a metapackage designed to prevent this, by making it impossible to install
`mkl`, but if your environment is already broken it may not work.
Or this (which takes forever on my computer and didn't work anyway). Do *not* use `os.environ['KMP_DUPLICATE_LIB_OK']='True'` or equivalents as this
masks the underlying issue of using Intel packages.
conda install nomkl
This error happens with Anaconda on Macs, and
[nomkl](https://stackoverflow.com/questions/66224879/what-is-the-nomkl-python-package-used-for)
is supposed to fix the issue (it isn't a module but a fix of some
sort). [There's more
suggestions](https://stackoverflow.com/questions/53014306/error-15-initializing-libiomp5-dylib-but-found-libiomp5-dylib-already-initial),
like uninstalling tensorflow and reinstalling. I haven't tried them.
Since I switched to miniforge I haven't seen the error.
### Not enough memory. ### Not enough memory.
@ -226,4 +211,8 @@ What? Intel? On an Apple Silicon?
The processor must support the Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) instructions. The processor must support the Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) instructions.
The processor must support the Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions. The processor must support the Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.
This was actually the issue that I couldn't solve until I switched to miniforge. This is due to the Intel `mkl` package getting picked up when you try to install
something that depends on it-- Rosetta can translate some Intel instructions but
not the specialized ones here. To avoid this, make sure to use the environment
variable `CONDA_SUBDIR=osx-arm64`, which restricts the Conda environment to only
use ARM packages, and use `nomkl` as described above.

68
environment-mac.yaml
View File

@ -1,33 +1,57 @@
name: ldm name: ldm
channels: channels:
- apple
- conda-forge
- pytorch-nightly - pytorch-nightly
- defaults - conda-forge
dependencies: dependencies:
- python=3.10.4 - python==3.9.13
- pip=22.1.2 - pip==22.2.2
# pytorch-nightly, left unpinned
- pytorch - pytorch
- torchmetrics
- torchvision - torchvision
- numpy=1.23.1
- pip: # I suggest to keep the other deps sorted for convenience.
- albumentations==0.4.6 # If you wish to upgrade to 3.10, try to run this:
- opencv-python==4.6.0.66 #
- pudb==2019.2 # ```shell
- imageio==2.9.0 # CONDA_CMD=conda
- imageio-ffmpeg==0.4.2 # sed -E 's/python==3.9.13/python==3.10.5/;s/ldm/ldm-3.10/;21,99s/- ([^=]+)==.+/- \1/' environment-mac.yaml > /tmp/environment-mac-updated.yml
- pytorch-lightning==1.4.2 # CONDA_SUBDIR=osx-arm64 $CONDA_CMD env create -f /tmp/environment-mac-updated.yml && $CONDA_CMD list -n ldm-3.10 | awk ' {print " - " $1 "==" $2;} '
# ```
#
# Unfortunately, as of 2022-08-31, this fails at the pip stage.
- albumentations==1.2.1
- coloredlogs==15.0.1
- einops==0.4.1
- grpcio==1.46.4
- humanfriendly
- imageio-ffmpeg==0.4.7
- imageio==2.21.2
- imgaug==0.4.0
- kornia==0.6.7
- mpmath==1.2.1
- nomkl
- numpy==1.23.2
- omegaconf==2.1.1 - omegaconf==2.1.1
- test-tube>=0.7.5 - onnx==1.12.0
- streamlit==1.12.0 - onnxruntime==1.12.1
- pillow==9.2.0 - opencv==4.6.0
- einops==0.3.0 - pudb==2022.1
- torch-fidelity==0.3.0 - pytorch-lightning==1.6.5
- transformers==4.19.2 - scipy==1.9.1
- torchmetrics==0.6.0 - streamlit==1.12.2
- kornia==0.6.0 - sympy==1.10.1
- -e git+https://github.com/openai/CLIP.git@main#egg=clip - tensorboard==2.9.0
- transformers==4.21.2
- pip:
- invisible-watermark
- test-tube
- tokenizers
- torch-fidelity
- -e git+https://github.com/huggingface/diffusers.git@v0.2.4#egg=diffusers
- -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
- -e git+https://github.com/openai/CLIP.git@main#egg=clip
- -e git+https://github.com/lstein/k-diffusion.git@master#egg=k-diffusion - -e git+https://github.com/lstein/k-diffusion.git@master#egg=k-diffusion
- -e . - -e .
variables: variables:

5
ldm/simplet2i.py
View File

@ -272,14 +272,15 @@ class T2I:
if not(width == self.width and height == self.height): if not(width == self.width and height == self.height):
width, height, _ = self._resolution_check(width, height, log=True) width, height, _ = self._resolution_check(width, height, log=True)
scope = autocast if self.precision == 'autocast' else nullcontext scope = autocast if self.precision == 'autocast' and torch.cuda.is_available() else nullcontext
if sampler_name and (sampler_name != self.sampler_name): if sampler_name and (sampler_name != self.sampler_name):
self.sampler_name = sampler_name self.sampler_name = sampler_name
self._set_sampler() self._set_sampler()
tic = time.time() tic = time.time()
torch.cuda.reset_peak_memory_stats() if self.device == 'cuda' else None if torch.cuda.is_available():
torch.cuda.reset_peak_memory_stats()
results = list() results = list()
try: try: