peaashmeter / invoke-ai-gui-colab

An attempt to run latest release of Invoke Ai's web gui through Google Colab

Dart/Flutter developer, Discord enthusiast, LLM enjoyer.

Check also https://peaashmeter.dev/.

invoke-ai-gui-colab's Issues

How can i change to anther model which i want?

please tell me how to do that,thanks

is it possible to dump ngrok and use gradio?

Bro,

Ur code just works fine with almost all models with the tweaking in yml file. I even made one for Kaggle but as kaggle doesnt allow tunnelling via ngrok, it got me banned.

So, I was thinking if its possible to dump ngrok tunnel and use gradio with --share ,..

I'm noob with gradio n all, so if u can convert this code with gradio for kaggle, will be thankful.

can't add any other models like stable diffusion and inpainting

Please if you can add an easy way for people to add custom models that would be very helpful
Thanks!

Use another model in google colab

I'm having trouble to use another model than anything v3, there is any way that i can upload more models to invoke ai in google colab ? I have some trained models and downloaded models that i like to use, waiting for an answer, thanks to you for this good project (Sorry for any english mistakes)

Invoke ai new versions on colab

Hello, I recently made a comment so I apologize for making another one but I have a question. The github repository of invoke ai seems to be on version 2.2.5 and it also appears in the output when executing commands in colab, however when I opened the file the version does not seem updated, it does not present the new functions of version 2.2.5, I would like to know if there is any way to use the updated version, thank you (Sorry for any English errors)

can't run it(

not into collab and all that tweaks at all,my bad. but really want to try things out from the the artistic side. Can you please lead me through correct installation? Ive done all steps till the last one. got the ngrok token. but there was something like an error

Scanning Model: Anything_v3_vaefixed
** model Anything_v3_vaefixed could not be loaded: pickle exhausted before seeing STOP
Traceback (most recent call last):
File "/home/InvokeAI/ldm/invoke/model_cache.py", line 81, in get_model
requested_model, width, height, hash = self._load_model(model_name)
File "/home/InvokeAI/ldm/invoke/model_cache.py", line 222, in _load_model
self.scan_model(model_name, weights)
File "/home/InvokeAI/ldm/invoke/model_cache.py", line 312, in scan_model
scan_result = scan_file_path(checkpoint)
File "/usr/local/envs/invokeai/lib/python3.9/site-packages/picklescan/scanner.py", line 366, in scan_file_path
return scan_bytes(file, path, file_ext)
File "/usr/local/envs/invokeai/lib/python3.9/site-packages/picklescan/scanner.py", line 300, in scan_bytes
return scan_pytorch(data, file_id)
File "/usr/local/envs/invokeai/lib/python3.9/site-packages/picklescan/scanner.py", line 288, in scan_pytorch
magic = get_magic_number(data)
File "/usr/local/envs/invokeai/lib/python3.9/site-packages/picklescan/torch.py", line 77, in get_magic_number
for opcode, args, _pos in genops(data):
File "/usr/local/envs/invokeai/lib/python3.9/pickletools.py", line 2283, in _genops
raise ValueError("pickle exhausted before seeing STOP")
ValueError: pickle exhausted before seeing STOP

!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
You appear to have a missing or misconfigured model file(s).
The script will now exit and run configure_invokeai.py to help fix the problem.
After reconfiguration is done, please relaunch invoke.py.
!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
configure_invokeai is launching....

Loading Python libraries...

Welcome to InvokeAI. This script will help download the Stable Diffusion weight files
and other large models that are needed for text to image generation. At any point you may interrupt
this program and resume later.

** DOWNLOADING DIFFUSION WEIGHTS **
You can download and configure the weights files manually or let this
script do it for you. Manual installation is described at:

https://invoke-ai.github.io/InvokeAI/installation/020_INSTALL_MANUAL/

You may download the recommended models (about 10GB total), select a customized set, or
completely skip this step.

Download ecommended models, ll models, ustomized list, or kip this step? [r]: r
** LICENSE AGREEMENT FOR WEIGHT FILES **

By downloading the Stable Diffusion weight files from the official Hugging Face
repository, you agree to have read and accepted the CreativeML Responsible AI License.
The license terms are located here:

https://huggingface.co/spaces/CompVis/stable-diffusion-license

Accept the above License terms? [y] y
Thank you!

Authenticating to Huggingface
Huggingface token not found in cache.
Token was not found in the environment variable HUGGING_FACE_HUB_TOKEN.
Token was not found in the environment variable HUGGINGFACE_TOKEN.

You may optionally enter your Huggingface token now. InvokeAI will work without it, but some functionality may be limited.
See https://invoke-ai.github.io/InvokeAI/features/CONCEPTS/#using-a-hugging-face-concept for more information.

Visit https://huggingface.co/settings/tokens to generate a token. (Sign up for an account if needed).

Paste the token below using Ctrl-Shift-V (macOS/Linux) or right-click (Windows), and/or 'Enter' to continue.
You may re-run the configuration script again in the future if you do not wish to set the token right now.

so im got the hugginface token downloaded recommended models and ended up with that:

** Model Installation Successful **

You're all set!

If you installed using one of the automated installation scripts,
execute 'invoke.sh' (Linux/macOS) or 'invoke.bat' (Windows) to
start InvokeAI.

If you installed manually, activate the 'invokeai' environment
(e.g. 'conda activate invokeai'), then run one of the following
commands to start InvokeAI.

Web UI:
python scripts/invoke.py --web # (connect to http://localhost:9090/)
Command-line interface:
python scripts/invoke.py

Have fun!

ERR_NGROK_8012 plus ConstructorError

I am zero in coding. But, please, if you can help, this error keeps persisting, even in paid collab subscriptions. On click on URL link I get this ERR_NGROK_8012. That guy in the video doesn't help, as I said, I m dummie, I have no idea what he is doing. Also at the end this : ConstructorError: while constructing a mapping
in "/root/invokeai/configs/models.yaml", line 2, column 2
found duplicate key weights
in "/root/invokeai/configs/models.yaml", line 10, column 2

If you could give me a simple step by step what to do, I would be more than happy.

Custom Model without Mount and another error

Nice work
but i wanna ask, Is mounting to gdrive a must? .
Im trying to delete mounting gdrive, downloading custom model, edit yaml for custom model but its keep cant run when last cell.

this command also give me error so i make new folder

%mkdir -p /root/invokeai/configs/ 
%cp ../invoke-ai-gui-colab/models.yaml /root/invokeai/configs 

its better if not using mounted gdrive and download manually model / custom model.
like this

import os

os.system('cd /')
os.system('mkdir -p /root/invokeai/models/ldm/stable-diffusion-v1')
os.system('wget -O /root/invokeai/models/ldm/stable-diffusion-v1/Anything-V3.0-pruned.ckpt https://huggingface.co/Linaqruf/anything-v3.0/resolve/main/Anything-V3.0-pruned.ckpt')
os.system('wget -O /root/invokeai/models/ldm/stable-diffusion-v1/Anything-V3.0.vae.pt https://huggingface.co/Linaqruf/anything-v3.0/resolve/main/Anything-V3.0.vae.pt')
os.system('wget -O /root/invokeai/models/ldm/stable-diffusion-v1/vae-ft-mse-840000-ema-pruned.ckpt https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/vae-ft-mse-840000-ema-pruned.ckpt')

waiting for update

fatal: not a git repository

"fatal: not a git repository" on "Подготовка репозитория Invoke Ai" stage

Cloning into 'invoke-ai-gui-colab'...

remote: Enumerating objects: 77, done.
remote: Counting objects: 100% (77/77), done.
remote: Compressing objects: 100% (64/64), done.
remote: Total 77 (delta 42), reused 30 (delta 13), pack-reused 0
Unpacking objects: 100% (77/77), done.
fatal: not a git repository (or any of the parent directories): .git
/home/invoke-ai-gui-colab

To produce:

Run sequentially up to stage 2

Pyngrok error

Server no more starts because:

ModuleNotFoundError Traceback (most recent call last)
in <cell line: 9>()
7
8 import os
----> 9 from pyngrok import ngrok
10
11 ngrok.kill()

ModuleNotFoundError: No module named 'pyngrok'