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

update TROUBLESHOOT.md

Browse Source
This commit is contained in:
mauwii 2022-11-06 17:07:27 +01:00 committed by Lincoln Stein
parent 7f150ed833
commit c7984f3299
1 changed files with 50 additions and 49 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

95
docs/help/TROUBLESHOOT.md
View File

@ -1,23 +1,21 @@
--- ---
title: F.A.Q. title: F.A.Q.
hide:
- toc
--- ---
# :material-frequently-asked-questions: F.A.Q. # :material-frequently-asked-questions: F.A.Q.
## **Frequently-Asked-Questions** ## **Frequently-Asked-Questions**
Here are a few common installation problems and their solutions. Often these are caused by Here are a few common installation problems and their solutions. Often these are
incomplete installations or crashes during the install process. caused by incomplete installations or crashes during the install process.
--- ---
### **QUESTION** ### During `conda env create`, conda hangs indefinitely
During `conda env create`, conda hangs indefinitely. If it is because of the last PIP step (usually stuck in the Git Clone step, you
can check the detailed log by this method):
If it is because of the last PIP step (usually stuck in the Git Clone step, you can check the detailed log by this method):
```bash ```bash
export PIP_LOG="/tmp/pip_log.txt" export PIP_LOG="/tmp/pip_log.txt"
touch ${PIP_LOG} touch ${PIP_LOG}
@ -29,14 +27,13 @@ rm ${PIP_LOG}
**SOLUTION** **SOLUTION**
Conda sometimes gets stuck at the last PIP step, in which several git repositories are Conda sometimes gets stuck at the last PIP step, in which several git
cloned and built. repositories are cloned and built.
Enter the stable-diffusion directory and completely remove the `src` Enter the stable-diffusion directory and completely remove the `src` directory
directory and all its contents. The safest way to do this is to enter and all its contents. The safest way to do this is to enter the stable-diffusion
the stable-diffusion directory and give the command `git clean -f`. If directory and give the command `git clean -f`. If this still doesn't fix the
this still doesn't fix the problem, try "conda clean -all" and then problem, try "conda clean -all" and then restart at the `conda env create` step.
restart at the `conda env create` step.
To further understand the problem to checking the install lot using this method: To further understand the problem to checking the install lot using this method:
@ -51,43 +48,44 @@ rm ${PIP_LOG}
--- ---
### **QUESTION** ### `invoke.py` crashes with the complaint that it can't find `ldm.simplet2i.py`
`invoke.py` crashes with the complaint that it can't find `ldm.simplet2i.py`. Or it complains that Or it complains that function is being passed incorrect parameters.
function is being passed incorrect parameters.
### **SOLUTION** **SOLUTION**
Reinstall the stable diffusion modules. Enter the `stable-diffusion` directory and give the command Reinstall the stable diffusion modules. Enter the `stable-diffusion` directory
`pip install -e .` and give the command `pip install -e .`
--- ---
### **QUESTION** ### Missing modules
`invoke.py` dies, complaining of various missing modules, none of which starts with `ldm`. `invoke.py` dies, complaining of various missing modules, none of which starts
with `ldm`.
### **SOLUTION** **SOLUTION**
From within the `InvokeAI` directory, run `conda env update` This is also frequently the solution to From within the `InvokeAI` directory, run `conda env update` This is also
complaints about an unknown function in a module. frequently the solution to complaints about an unknown function in a module.
--- ---
### **QUESTION** ### How can I try new features
There's a feature or bugfix in the Stable Diffusion GitHub that you want to try out. There's a feature or bugfix in the Stable Diffusion GitHub that you want to try
out.
### **SOLUTION** **SOLUTIONS**
#### **Main Branch** #### **Main Branch**
If the fix/feature is on the `main` branch, enter the stable-diffusion directory and do a If the fix/feature is on the `main` branch, enter the stable-diffusion directory
`git pull`. and do a `git pull`.
Usually this will be sufficient, but if you start to see errors about Usually this will be sufficient, but if you start to see errors about missing or
missing or incorrect modules, use the command `pip install -e .` incorrect modules, use the command `pip install -e .` and/or `conda env update`
and/or `conda env update` (These commands won't break anything.) (These commands won't break anything.)
`pip install -e .` and/or `conda env update -f environment.yaml` `pip install -e .` and/or `conda env update -f environment.yaml`
@ -95,33 +93,36 @@ and/or `conda env update` (These commands won't break anything.)
#### **Sub Branch** #### **Sub Branch**
If the feature/fix is on a branch (e.g. "_foo-bugfix_"), the recipe is similar, but do a If the feature/fix is on a branch (e.g. "_foo-bugfix_"), the recipe is similar,
`git pull <name of branch>`. but do a `git pull <name of branch>`.
#### **Not Committed** #### **Not Committed**
If the feature/fix is in a pull request that has not yet been made part of the main branch or a If the feature/fix is in a pull request that has not yet been made part of the
feature/bugfix branch, then from the page for the desired pull request, look for the line at the top main branch or a feature/bugfix branch, then from the page for the desired pull
that reads "_xxxx wants to merge xx commits into lstein:main from YYYYYY_". Copy the URL in YYYY. It request, look for the line at the top that reads "_xxxx wants to merge xx
should have the format commits into lstein:main from YYYYYY_". Copy the URL in YYYY. It should have the
format
`https://github.com/<name of contributor>/stable-diffusion/tree/<name of branch>` `https://github.com/<name of contributor>/stable-diffusion/tree/<name of branch>`
Then **go to the directory above stable-diffusion** and rename the directory to Then **go to the directory above stable-diffusion** and rename the directory to
"_stable-diffusion.lstein_", "_stable-diffusion.old_", or anything else. You can then git clone the "_stable-diffusion.lstein_", "_stable-diffusion.old_", or anything else. You can
branch that contains the pull request: then git clone the branch that contains the pull request:
`git clone https://github.com/<name of contributor>/stable-diffusion/tree/<name of branch>` `git clone https://github.com/<name of contributor>/stable-diffusion/tree/<name of branch>`
You will need to go through the install procedure again, but it should be fast because all the You will need to go through the install procedure again, but it should be fast
dependencies are already loaded. because all the dependencies are already loaded.
--- ---
### **QUESTION** ### CUDA out of memory
Image generation crashed with CUDA out of memory error after successful sampling. Image generation crashed with CUDA out of memory error after successful
sampling.
### **SOLUTION** **SOLUTION**
Try to run script with option `--free_gpu_mem` This will free memory before image decoding step. Try to run script with option `--free_gpu_mem` This will free memory before
image decoding step.