Merge branch 'spezialspezial-patch-9' into development

.github/workflows/mkdocs-material.yml

@@ -4,6 +4,7 @@ on:
     branches:
       - 'main'
       - 'development'
+      - 'release-candidate-2-1'
 
 jobs:
   mkdocs-material:

docs/installation/INSTALL_LINUX.md

@@ -43,6 +43,7 @@ title: Manual Installation, Linux
    environment named `invokeai` and activate the environment.
 
     ```bash
+    (base) rm -rf src      # (this is a precaution in case there is already a src directory)
     (base) ~/InvokeAI$ conda env create
     (base) ~/InvokeAI$ conda activate invokeai
     (invokeai) ~/InvokeAI$
@@ -51,50 +52,54 @@ title: Manual Installation, Linux
     After these steps, your command prompt will be prefixed by `(invokeai)` as shown
     above.
 
-6. Load a couple of small machine-learning models required by stable diffusion:
+6. Load the big stable diffusion weights files and a couple of smaller machine-learning models:
 
     ```bash
     (invokeai) ~/InvokeAI$ python3 scripts/preload_models.py
     ```
 
     !!! note
+    	This script will lead you through the process of creating an account on Hugging Face,
+	accepting the terms and conditions of the Stable Diffusion model license, and
+	obtaining an access token for downloading. It will then download and install the
+	weights files for you.
 
-        This step is necessary because I modified the original just-in-time
+	Please see [../features/INSTALLING_MODELS.md] for a manual process for doing the
-        model loading scheme to allow the script to work on GPU machines that are not
+	same thing.
-        internet connected. See [Preload Models](../features/OTHER.md#preload-models)
 
-7. Install the weights for the stable diffusion model.
+7. Start generating images!
 
-- Sign up at https://huggingface.co
+    # Command-line interface
-- Go to the [Stable diffusion diffusion model page](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original)
+    (invokeai) python scripts/invoke.py
-- Accept the terms and click Access Repository
-- Download [v1-5-pruned-emaonly.ckpt (4.27 GB)](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt)
-and move it into this directory under `models/ldm/stable_diffusion_v1/v1-5-pruned-emaonly.ckpt`
 
-There are many other models that you can use. Please see [../features/INSTALLING_MODELS.md]
+    # or run the web interface on localhost:9090!
-for details.
+    (invokeai) python scripts/invoke.py --web
 
-8. Start generating images!
+    # or run the web interface on your machine's network interface!
+    (invokeai) python scripts/invoke.py --web --host 0.0.0.0
 
-    ```bash
+To use an alternative model you may invoke the `!switch` command in
-    # for the pre-release weights use the -l or --liaon400m switch
+the CLI, or pass `--model <model_name>` during `invoke.py` launch for
-    (invokeai) ~/InvokeAI$ python3 scripts/invoke.py -l
+either the CLI or the Web UI. See [Command Line
+Client](../features/CLI.md#model-selection-and-importation). The
+model names are defined in `configs/models.yaml`.
 
-    # for the post-release weights do not use the switch
+9. Subsequently, to relaunch the script, be sure to run "conda
-    (invokeai) ~/InvokeAI$ python3 scripts/invoke.py
+activate invokeai" (step 5, second command), enter the `InvokeAI`
-
+directory, and then launch the invoke script (step 8). If you forget
-    # for additional configuration switches and arguments, use -h or --help
+to activate the 'invokeai' environment, the script will fail with
-    (invokeai) ~/InvokeAI$ python3 scripts/invoke.py -h
+multiple `ModuleNotFound` errors.
-    ```
-
-9. Subsequently, to relaunch the script, be sure to run "conda activate invokeai" (step 5, second command), enter the `InvokeAI` directory, and then launch the invoke script (step 8). If you forget to activate the 'invokeai' environment, the script will fail with multiple `ModuleNotFound` errors.
 
 ## Updating to newer versions of the script
 
-This distribution is changing rapidly. If you used the `git clone` method (step 5) to download the InvokeAI directory, then to update to the latest and greatest version, launch the Anaconda window, enter `InvokeAI` and type:
+This distribution is changing rapidly. If you used the `git clone`
+method (step 5) to download the InvokeAI directory, then to update to
+the latest and greatest version, launch the Anaconda window, enter
+`InvokeAI` and type:
 
 ```bash
 (invokeai) ~/InvokeAI$ git pull
+(invokeai) ~/InvokeAI$ rm -rf src   # prevents conda freezing errors
 (invokeai) ~/InvokeAI$ conda env update -f environment.yml
 ```
 

docs/installation/INSTALL_MAC.md

@@ -19,24 +19,9 @@ an issue on Github and we will do our best to help.
 
 ## Installation
 
-First you need to download a large checkpoint file.
-
-1. Sign up at https://huggingface.co
-2. Go to the [Stable diffusion diffusion model page](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original)
-3. Accept the terms and click Access Repository
-4. Download [v1-5-pruned-emaonly.ckpt (4.27 GB)](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt)
-and move it into this directory under `models/ldm/stable_diffusion_v1/v1-5-pruned-emaonly.ckpt`
-
-There are many other models that you can try. Please see [../features/INSTALLING_MODELS.md]
-for details.
-
-While that is downloading, open Terminal and run the following
-commands one at a time, reading the comments and taking care to run
-the appropriate command for your Mac's architecture (Intel or M1).
-
 !!! todo "Homebrew"
 
-    If you have no brew installation yet (otherwise skip):
+    First you will install the "brew" package manager. Skip this if brew is already installed.
 
     ```bash title="install brew (and Xcode command line tools)"
     /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"
@@ -100,25 +85,6 @@ the appropriate command for your Mac's architecture (Intel or M1).
     cd InvokeAI
     ```
 
-!!! todo "Wait until the checkpoint-file download finished, then proceed"
-
-    We will leave the big checkpoint wherever you stashed it for long-term storage,
-    and make a link to it from the repo's folder. This allows you to use it for
-    other repos, or if you need to delete Invoke AI, you won't have to download it again.
-
-    ```{.bash .annotate}
-    # Make the directory in the repo for the symlink
-    mkdir -p models/ldm/stable-diffusion-v1/
-
-    # This is the folder where you put the checkpoint file `sd-v1-4.ckpt`
-    PATH_TO_CKPT="$HOME/Downloads" # (1)!
-
-    # Create a link to the checkpoint
-    ln -s "$PATH_TO_CKPT/sd-v1-4.ckpt" models/ldm/stable-diffusion-v1/model.ckpt
-    ```
-
-    1. replace `$HOME/Downloads` with the Location where you actually stored the Checkppoint (`sd-v1-4.ckpt`)
-
 !!! todo "Create the environment & install packages"
 
     === "M1 Mac"
@@ -137,25 +103,40 @@ the appropriate command for your Mac's architecture (Intel or M1).
     # Activate the environment (you need to do this every time you want to run SD)
     conda activate invokeai
 
-    # This will download some bits and pieces and make take a while
-    (invokeai) python scripts/preload_models.py
-
-    # Run SD!
-    (invokeai) python scripts/dream.py
-
-    # or run the web interface!
-    (invokeai) python scripts/invoke.py --web
-
-    # The original scripts should work as well.
-    (invokeai) python scripts/orig_scripts/txt2img.py \
-        --prompt "a photograph of an astronaut riding a horse" \
-        --plms
-    ```
     !!! info
 
         `export PIP_EXISTS_ACTION=w` is a precaution to fix `conda env
         create -f environment-mac.yml` never finishing in some situations. So
-        it isn't required but wont hurt.
+        it isn't required but won't hurt.
+
+!!! todo "Download the model weight files"
+
+The `preload_models.py` script downloads and installs the model weight
+files for you. It will lead you through the process of getting a Hugging Face
+account, accepting the Stable Diffusion model weight license agreement, and
+creating a download token:
+
+    # This will take some time, depending on the speed of your internet connection
+    # and will consume about 10GB of space
+    (invokeai) python scripts/preload_models.py
+
+!! todo "Run InvokeAI!"
+
+    # Command-line interface
+    (invokeai) python scripts/invoke.py
+
+    # or run the web interface on localhost:9090!
+    (invokeai) python scripts/invoke.py --web
+
+    # or run the web interface on your machine's network interface!
+    (invokeai) python scripts/invoke.py --web --host 0.0.0.0
+
+To use an alternative model you may invoke the `!switch` command in
+the CLI, or pass `--model <model_name>` during `invoke.py` launch for
+either the CLI or the Web UI. See [Command Line
+Client](../features/CLI.md#model-selection-and-importation). The
+model names are defined in `configs/models.yaml`.
+
 ---
 
 ## Common problems

docs/installation/INSTALL_WINDOWS.md

@@ -69,40 +69,42 @@ in the wiki
     environment file isn't specified, conda will default to `environment.yml`. You will need
     to provide the `-f` option if you wish to load a different environment file at any point.
 
-7. Run the command:
+7. Load the big stable diffusion weights files and a couple of smaller machine-learning models:
 
-    ```batch
+    ```bash
-    python scripts\preload_models.py
+    (invokeai) ~/InvokeAI$ python3 scripts/preload_models.py
     ```
 
-    This installs several machine learning models that stable diffusion requires.
+    !!! note
+    	This script will lead you through the process of creating an account on Hugging Face,
+	accepting the terms and conditions of the Stable Diffusion model license, and
+	obtaining an access token for downloading. It will then download and install the
+	weights files for you.
 
-    Note: This step is required. This was done because some users may might be
+	Please see [../features/INSTALLING_MODELS.md] for a manual process for doing the
-    blocked by firewalls or have limited internet connectivity for the models to
+	same thing.
-    be downloaded just-in-time.
 
-8. Now you need to install the weights for the big stable diffusion model.
+8. Start generating images!
 
-   - Sign up at https://huggingface.co
+    # Command-line interface
-   - Go to the [Stable diffusion diffusion model page](https://huggingface.co/CompVis/stable-diffusion-v-1-4-original)
+    (invokeai) python scripts/invoke.py
-   - Accept the terms and click Access Repository
-   - Download [v1-5-pruned-emaonly.ckpt (4.27 GB)](https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt)
-     and move it into this directory under `models/ldm/stable_diffusion_v1/v1-5-pruned-emaonly.ckpt`
 
-   There are many other models that you can use. Please see [../features/INSTALLING_MODELS.md]
+    # or run the web interface on localhost:9090!
-   for details.
+    (invokeai) python scripts/invoke.py --web
 
-9. Start generating images!
+    # or run the web interface on your machine's network interface!
+    (invokeai) python scripts/invoke.py --web --host 0.0.0.0
 
-    ```batch title="for the pre-release weights"
+To use an alternative model you may invoke the `!switch` command in
-    python scripts\invoke.py -l
+the CLI, or pass `--model <model_name>` during `invoke.py` launch for
-    ```
+either the CLI or the Web UI. See [Command Line
+Client](../features/CLI.md#model-selection-and-importation). The
+model names are defined in `configs/models.yaml`.
 
-    ```batch title="for the post-release weights"
+9. Subsequently, to relaunch the script, first activate the Anaconda
-    python scripts\invoke.py
+command window (step 3),enter the InvokeAI directory (step 5, `cd
-    ```
+\path\to\InvokeAI`), run `conda activate invokeai` (step 6b), and then
-
+launch the invoke script (step 9).
-10. Subsequently, to relaunch the script, first activate the Anaconda command window (step 3),enter the InvokeAI directory (step 5, `cd \path\to\InvokeAI`), run `conda activate invokeai` (step 6b), and then launch the invoke script (step 9).
 
 !!! tip "Tildebyte has written an alternative"
 

environment-linux-aarch64.yml

@@ -11,6 +11,7 @@ dependencies:
   - numpy=1.19
   - imageio=2.9.0
   - opencv=4.6.0
+  - getpass_asterisk
   - pillow=8.*
   - flask=2.1.*
   - flask_cors=3.0.10

environment-mac.yml

@@ -22,6 +22,7 @@ dependencies:
   - diffusers=0.6.0
   - einops=0.4.1
   - grpcio=1.46.4
+  - getpass_asterisk
   - humanfriendly=10.0
   - imageio=2.21.2
   - imageio-ffmpeg=0.4.7

environment.yml

@@ -1,14 +1,14 @@
 name: invokeai
 channels:
   - pytorch
+  - nvidia
   - defaults
 dependencies:
   - python>=3.9
-  - pip=20.3
+  - pip=22.2.2
-  - cudatoolkit=11.3
+  - numpy=1.23.3
-  - pytorch=1.11.0
+  - torchvision=0.14.0
-  - torchvision=0.12.0
+  - pytorch-cuda=11.7
-  - numpy=1.19.2
   - pip:
     - albumentations==0.4.3
     - opencv-python==4.5.5.64
@@ -33,6 +33,7 @@ dependencies:
     - flask_cors==3.0.10
     - dependency_injector==4.40.0
     - eventlet
+    - getpass_asterisk
     - kornia==0.6.0
     - -e git+https://github.com/openai/CLIP.git@main#egg=clip
     - -e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers

installer/install.bat

@@ -80,14 +80,36 @@ if not exist ".git" (
 call conda activate
 
 @rem create the environment
+call conda env remove -n invokeai
 call conda env create
-call conda activate invokeai
+if "%ERRORLEVEL%" NEQ "0" (
+   echo ""
+   echo "Something went wrong while installing Python libraries and cannot continue.
+   echo "Please visit https://invoke-ai.github.io/InvokeAI/#installation for alternative"
+   echo "installation methods."
+   echo "Press any key to continue"
+   pause
+   exit /b
+)
 
+call conda activate invokeai
 @rem preload the models
 call python scripts\preload_models.py
+if "%ERRORLEVEL%" NEQ "0" (
+   echo ""
+   echo "The preload_models.py script crashed or was cancelled."
+   echo "InvokeAI is not ready to run. To run preload_models.py again,"
+   echo "run the command 'update.bat' in this directory."
+   echo "Press any key to continue"
+   pause
+   exit /b
+)
 
 @rem tell the user their next steps
-echo.
+echo ""
+echo "* InvokeAI installed successfully *"
 echo "You can now start generating images by double-clicking the 'invoke.bat' file (inside this folder)
-
+echo "Press any key to continue"
 pause
+exit 0
+

installer/install.sh

@@ -99,13 +99,32 @@ conda activate
 if [ "$OS_NAME" == "mac" ]; then
     PIP_EXISTS_ACTION=w CONDA_SUBDIR=osx-${OS_ARCH} conda env create -f environment-mac.yml
 else
+    conda env remove -n invokeai
     conda env create -f environment.yml
 fi
 
+status=$?
+
+if test $status -ne 0
+then
+   echo "Something went wrong while installing Python libraries and cannot continue."
+   echo "Please visit https://invoke-ai.github.io/InvokeAI/#installation for alternative"
+   echo "installation methods"
+else
+    conda activate invokeai
+    # preload the models
+    echo "Calling the preload_models.py script"
+    python scripts/preload_models.py
+    status=$?
+    if test $status -ne 0
+       then
+	   echo "The preload_models.py script crashed or was cancelled."
+           echo "InvokeAI is not ready to run. Try again by running"
+           echo "update.sh in this directory."
+       else
+           # tell the user their next steps
+	   echo "You can now start generating images by running invoke.sh (inside this folder), using ./invoke.sh"
+       fi
+fi   
+
 conda activate invokeai
-
-# preload the models
-python scripts/preload_models.py
-
-# tell the user their next steps
-echo "You can now start generating images by running invoke.sh (inside this folder), using ./invoke.sh"

ldm/generate.py

@@ -896,7 +896,7 @@ class Generate:
         assert os.path.exists(image_path), '** "{image_path}" not found. Please enter the name of an existing image file to mask **'
         basename,_ = os.path.splitext(os.path.basename(image_path))
         if self.txt2mask is None:
-            self.txt2mask  = Txt2Mask(device = self.device)
+            self.txt2mask  = Txt2Mask(device = self.device, refined=True)
         segmented  = self.txt2mask.segment(image_path,prompt)
         trans = segmented.to_transparent()
         inverse = segmented.to_transparent(invert=True)

ldm/invoke/restoration/outcrop.py

@@ -41,7 +41,7 @@ class Outcrop(object):
             height      = extended_image.height,
             init_img    = extended_image,
             strength    = 0.90,
-            image_callback = wrapped_callback,
+            image_callback = wrapped_callback if image_callback else None,
             seam_size = opt.seam_size or 96,
             seam_blur = opt.seam_blur or 16,
             seam_strength = opt.seam_strength or 0.7,

ldm/invoke/txt2mask.py

@@ -36,6 +36,7 @@ from torchvision import transforms
 
 CLIP_VERSION = 'ViT-B/16'
 CLIPSEG_WEIGHTS = 'src/clipseg/weights/rd64-uni.pth'
+CLIPSEG_WEIGHTS_REFINED = 'src/clipseg/weights/rd64-uni-refined.pth'
 CLIPSEG_SIZE = 352
 
 class SegmentedGrayscale(object):
@@ -72,14 +73,14 @@ class Txt2Mask(object):
     Create new Txt2Mask object. The optional device argument can be one of
     'cuda', 'mps' or 'cpu'.
     '''
-    def __init__(self,device='cpu'):
+    def __init__(self,device='cpu',refined=False):
         print('>> Initializing clipseg model for text to mask inference')
         self.device = device
-        self.model = CLIPDensePredT(version=CLIP_VERSION, reduce_dim=64, )
+        self.model = CLIPDensePredT(version=CLIP_VERSION, reduce_dim=64, complex_trans_conv=refined)
         self.model.eval()
         # initially we keep everything in cpu to conserve space
         self.model.to('cpu')
-        self.model.load_state_dict(torch.load(CLIPSEG_WEIGHTS, map_location=torch.device('cpu')), strict=False)
+        self.model.load_state_dict(torch.load(CLIPSEG_WEIGHTS_REFINED if refined else CLIPSEG_WEIGHTS, map_location=torch.device('cpu')), strict=False)
 
     @torch.no_grad()
     def segment(self, image, prompt:str) -> SegmentedGrayscale:

requirements-mac-MPS-CPU.txt

@@ -1,6 +1,6 @@
 -r requirements.txt
 
 protobuf==3.19.6
-torch
+torch<1.13.0
-torchvision
+torchvision<0.14.0
 -e .

requirements.txt

@@ -2,6 +2,7 @@
 
 albumentations
 einops
+getpass_asterisk
 huggingface-hub
 imageio-ffmpeg
 imageio
@@ -13,7 +14,7 @@ opencv-python
 pillow
 pip>=22
 pudb
-pytorch-lightning=1.7.7
+pytorch-lightning==1.7.7
 scikit-image>=0.19
 streamlit
 pyreadline3

scripts/preload_models.py

@@ -14,18 +14,21 @@ import warnings
 from urllib import request
 from tqdm import tqdm
 from omegaconf import OmegaConf
+from huggingface_hub import HfFolder, hf_hub_url
 from pathlib import Path
+from getpass_asterisk import getpass_asterisk
 import traceback
-import getpass
 import requests
 import clip
 import transformers
 import torch
 transformers.logging.set_verbosity_error()
 
-# deferred loading so that help message can be printed quickly
+import warnings
-def load_libs():
+warnings.filterwarnings('ignore')
-    pass
+#warnings.simplefilter('ignore')
+#warnings.filterwarnings('ignore',category=DeprecationWarning)
+#warnings.filterwarnings('ignore',category=UserWarning)
 
 #--------------------------globals--
 Model_dir = './models/ldm/stable-diffusion-v1/'
@@ -98,7 +101,7 @@ this program and resume later.\n'''
 #--------------------------------------------
 def postscript():
     print(
-        '''You're all set! You may now launch InvokeAI using one of these two commands:
+        '''\n** Model Installation Successful **\nYou're all set! You may now launch InvokeAI using one of these two commands:
 Web version: 
 
     python scripts/invoke.py --web  (connect to http://localhost:9090)
@@ -220,10 +223,18 @@ This involves a few easy steps.
 '''
     )
     input('Press <enter> when you are ready to continue:')
+<<<<<<< HEAD
 
     from huggingface_hub import HfFolder
+=======
+    print('(Fetching Hugging Face token from cache...',end='')
+>>>>>>> spezialspezial-patch-9
     access_token = HfFolder.get_token()
+    if access_token is not None:
+        print('found')
+    
     if access_token is None:
+        print('not found')
         print('''
 4. Thank you! The last step is to enter your HuggingFace access token so that
    this script is authorized to initiate the download. Go to the access tokens
@@ -237,8 +248,7 @@ This involves a few easy steps.
 
    Now copy the token to your clipboard and paste it here: '''
         )
-        access_token = getpass.getpass()
+        access_token = getpass_asterisk.getpass_asterisk()
-        HfFolder.save_token(access_token)
     return access_token
 
 #---------------------------------------------
@@ -268,14 +278,26 @@ def download_weight_datasets(models:dict, access_token:str):
         )
         if success:
             successful[mod] = True
+    if len(successful) < len(models):
+        print(f'\n\n** There were errors downloading one or more files. **')
+        print('Please double-check your license agreements, and your access token.')
+        HfFolder.delete_token()
+        print('Press any key to try again. Type ^C to quit.\n')
+        input()
+        return None
+
+    HfFolder.save_token(access_token)
     keys = ', '.join(successful.keys())
     print(f'Successfully installed {keys}') 
     return successful
     
 #---------------------------------------------
 def download_with_resume(repo_id:str, model_name:str, access_token:str)->bool:
+<<<<<<< HEAD
     from huggingface_hub import hf_hub_url
 
+=======
+>>>>>>> spezialspezial-patch-9
     model_dest = os.path.join(Model_dir, model_name)
     os.makedirs(os.path.dirname(model_dest), exist_ok=True)
     url = hf_hub_url(repo_id, model_name)
@@ -295,6 +317,8 @@ def download_with_resume(repo_id:str, model_name:str, access_token:str)->bool:
     if resp.status_code==416:  # "range not satisfiable", which means nothing to return
         print(f'* {model_name}: complete file found. Skipping.')
         return True
+    elif resp.status_code != 200:
+        print(f'** An error occurred during downloading {model_name}: {resp.reason}')
     elif exist_size > 0:
         print(f'* {model_name}: partial file found. Resuming...')
     else:
@@ -302,7 +326,7 @@ def download_with_resume(repo_id:str, model_name:str, access_token:str)->bool:
 
     try:
         if total < 2000:
-            print(f'* {model_name}: {resp.text}')
+            print(f'*** ERROR DOWNLOADING {model_name}: {resp.text}')
             return False
 
         with open(model_dest, open_mode) as file, tqdm(
@@ -329,7 +353,11 @@ def update_config_file(successfully_downloaded:dict,opt:dict):
 
     try:
         if os.path.exists(Config_file):
+<<<<<<< HEAD
             print(f'** {Config_file} exists. Renaming to {Config_file}.orig')
+=======
+            print(f'* {Config_file} exists. Renaming to {Config_file}.orig')
+>>>>>>> spezialspezial-patch-9
             os.rename(Config_file,f'{Config_file}.orig')
         tmpfile = os.path.join(os.path.dirname(Config_file),'new_config.tmp')
         with open(tmpfile, 'w') as outfile:
@@ -383,26 +411,35 @@ def new_config_file_contents(successfully_downloaded:dict, Config_file:str)->str
 # this will preload the Bert tokenizer fles
 def download_bert():
     print('Installing bert tokenizer (ignore deprecation errors)...', end='')
+<<<<<<< HEAD
     from transformers import BertTokenizerFast, AutoFeatureExtractor
+=======
+    sys.stdout.flush()
+>>>>>>> spezialspezial-patch-9
     with warnings.catch_warnings():
         warnings.filterwarnings('ignore', category=DeprecationWarning)
+        from transformers import BertTokenizerFast, AutoFeatureExtractor
         tokenizer = BertTokenizerFast.from_pretrained('bert-base-uncased')
         print('...success')
-        sys.stdout.flush()
 
 #---------------------------------------------
 # this will download requirements for Kornia
 def download_kornia():
-    print('Installing Kornia requirements...', end='')
+    print('Installing Kornia requirements (ignore deprecation errors)...', end='')
-    with warnings.catch_warnings():
+    sys.stdout.flush()
-        warnings.filterwarnings('ignore', category=DeprecationWarning)
     import kornia
     print('...success')
 
 #---------------------------------------------
 def download_clip():
     print('Loading CLIP model...',end='')
+<<<<<<< HEAD
     from transformers import CLIPTokenizer, CLIPTextModel
+=======
+    with warnings.catch_warnings():
+        warnings.filterwarnings('ignore', category=DeprecationWarning)
+        from transformers import CLIPTokenizer, CLIPTextModel
+>>>>>>> spezialspezial-patch-9
     sys.stdout.flush()
     version = 'openai/clip-vit-large-patch14'
     tokenizer = CLIPTokenizer.from_pretrained(version)
@@ -531,7 +568,6 @@ if __name__ == '__main__':
                         default='./configs/models.yaml',
                         help='path to configuration file to create')
     opt = parser.parse_args()
-    load_libs()
     
     try:
         if opt.interactive:

update.bat

@@ -8,6 +8,12 @@ if exist ".git" (
     call git pull
 )
 
-conda env update
 
+conda env update
+conda activate invokeai
+python scripts/preload_models.py
+
+echo "Press any key to continue"
 pause
+exit 0
+

update.sh

@@ -20,3 +20,5 @@ case "${OS_NAME}" in
     Darwin*)    conda env update -f environment-mac.yml;;
     *)          echo "Unknown OS: $OS_NAME! This script runs only on Linux or Mac" && exit
 esac
+
+python scripts/preload_models.py