#Error starting invoke

21 messages · Page 1 of 1 (latest)

glossy bay
#

I just updated to 4.0.1 and now I get this error anytime I start Invoke.

image.png
prime lanternBOT
#

Hi @glossy bay. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

#

I'm sorry to hear that you're experiencing issues after updating Invoke AI. Based on the knowledge sources provided, there are a few steps you can take to troubleshoot this issue:

  1. Reinstall Invoke AI: Some users have reported that reinstalling Invoke AI fixed their startup issues. You can try downloading the installer for the version you're using and reinstalling it.

  2. Run the Configuration Script: The error message you're seeing might suggest that some necessary files are missing from your Invoke AI root directory. You can try rerunning the configuration script to fix this problem. From the launcher, select option [7]. From the command line, activate the virtual environment and run invokeai-configure --yes --skip-sd-weights.

  3. Check for Hidden Files in Model Directory: If you're using a Mac, check for hidden files in the model directory. Some users have reported that removing these files resolved their startup issues.

  4. Seek Help from the Community: If none of the above solutions work, you can create an issue on GitHub (https://github.com/invoke-ai/InvokeAI/issues) or post in the #help channel (https://discord.com/channels/1020123559063990373/1149510134058471514) of the InvokeAI Discord for further assistance.

Please note that these are general troubleshooting steps and the exact solution might vary depending on the specific error message you're seeing. If you could provide more details about the error, I might be able to give more specific advice.

#

@glossy bay kapa.ai is still learning and improving, please let us know how it did by reacting below

glossy bay
#

how do I activate the virtual environment

#

@prime lantern how do I activate the virtual environment

prime lanternBOT
#

Let me check the knowledge base for you. One moment! :books:

#

To activate the virtual environment for InvokeAI, you need to navigate to the root directory (also known as INVOKEAI_ROOT) where you installed InvokeAI and the virtual environment. The steps to activate the virtual environment differ slightly based on your operating system.

For Linux/Mac, use the following command:

source .venv/bin/activate

For Windows, use the following command:

.venv\Scripts\activate

After running these commands, you should see (.venv) in front of your prompt, indicating that the virtual environment is activated.

Please note that these commands assume that your virtual environment is named .venv and is located in the root directory of your InvokeAI installation. If you used a different name or location for your virtual environment, you will need to adjust these commands accordingly.

Source: InvokeAI Installation Walkthrough (https://invoke-ai.github.io/InvokeAI/installation/020_INSTALL_MANUAL#installation-walkthrough)

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@glossy bay kapa.ai is still learning and improving, please let us know how it did by reacting below

glossy bay
#

@prime lantern D:\users\jds77.venv\Scripts\python.exe: No module named invokeai.frontend.install.invokeai_update

prime lanternBOT
#

Let me check the knowledge base for you. One moment! :books:

#

The error message you're seeing suggests that Python can't find the invokeai.frontend.install.invokeai_update module. This could be due to a few reasons:

  1. InvokeAI is not installed in your virtual environment: You can install it using pip with the command pip install invokeai.

  2. Your virtual environment is not activated: Before running any InvokeAI commands, make sure to activate your virtual environment. For Windows, you can do this with the command .venv\Scripts\activate.

  3. The InvokeAI package is not up-to-date or is incorrectly installed: Try reinstalling InvokeAI in the same location as the old one. This should retain all old images and models.

If none of these solutions work, you might want to consider doing a clean install of InvokeAI. Remember to back up any important data before doing so.

Sources:

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@glossy bay kapa.ai is still learning and improving, please let us know how it did by reacting below

glossy bay
#

@prime lantern OSError: [WinError 126] The specified module could not be found. Error loading "D:\users\jds77.venv\lib\site-packages\torch\lib\torch_python.dll" or one of its dependencies.

prime lanternBOT
#

Let me check the knowledge base for you. One moment! :books:

#

The error message you're seeing suggests that Python can't find the torch_python.dll file in your Torch library. This could be due to a few reasons:

  1. Torch is not installed in your virtual environment: You can install it using pip with the command pip install torch.

  2. Your virtual environment is not activated: Before running any Torch commands, make sure to activate your virtual environment. For Windows, you can do this with the command .venv\Scripts\activate.

  3. The Torch package is not up-to-date or is incorrectly installed: Try reinstalling Torch in the same location as the old one.

If none of these solutions work, you might want to consider doing a clean install of Torch. Remember to back up any important data before doing so.

In some of the issues reported on the InvokeAI GitHub, users have faced similar problems with the 'torch' module not being found. A contributor suggested manually installing torch inside the virtual environment using the command pip install torch.

Sources:

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

#

@glossy bay kapa.ai is still learning and improving, please let us know how it did by reacting below

glossy bay
#

@prime lantern invalid model config exception

prime lanternBOT
#

Let me check the knowledge base for you. One moment! :books:

#

The InvalidModelConfigException is an error that occurs when there's an issue with the model configuration record in the InvokeAI database. This could happen if the configuration is not an instance of ModelConfigBase or a sparse dict containing the fields to be updated.

If you're encountering this error, it could be due to a few reasons:

  1. The model configuration is not correctly formatted: The configuration should be an instance of ModelConfigBase or a sparse dict containing the fields to be updated.

  2. The model configuration is not compatible with the base model: Each model can only be compatible with one base model. If a model is compatible with two or more base models, this could cause issues. A partial workaround is to use BaseModelType.Any, which indicates that the model is compatible with any of the base models.

  3. The model configuration is missing required fields: If required fields are missing from the model configuration, this could cause an InvalidModelConfigException.

If you're still having trouble after checking these potential issues, consider seeking help from the InvokeAI community on GitHub (https://github.com/invoke-ai/InvokeAI/issues) or Discord (https://discord.com/channels/1020123559063990373/1154395133643587667).

Sources:

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: