Comments (2)
lstein
commented on May 14, 2024
Yeah, I think you should be able to. These notebook apps can run arbitrary python packages, and I know that some have gotten this up and running on Google Colab. However, I'm not familiar with Gradient (or Colab for that matter) and I can't offer you any help with the install. If you do get it up and running on Gradient, would you be willing to write a brief HOWTO to help others along?
from invokeai.
GeorvityLabs
commented on May 14, 2024
@lstein , could you share the link to the colab notebook. (with textual inversion + inference using checkpoint)
I have trained in colab , but the issue comes when trying to run inference , "a photo of *" , it was failing on colab.
I have downloaded the checkpoint (.pt files) locally , and if you have a colab link I can test it out there.
from invokeai.
Related Issues (20)
- [bug]: 'argument of type 'NoneType' is not iterable' for training embeddings with SDXL HOT 3
- [bug]: ValueError: The SDXL LoRA could only be partially converted to diffusers format. converted=722, not_converted=560 HOT 7
- [enhancement]: Controlnet - Depth Hand Refiner HOT 2
- [enhancement]: Add model search capability
- [bug]: dw open pose don't work HOT 7
- [bug]: Issues with Invoke 3.7.0 install HOT 2
- [bug]: Get RuntimeError when using AMD gpu HOT 1
- [bug]: UI doesn't show labels HOT 17
- [bug]: Can't Launch or Fix Installation (MetadataIncompleteBuffer and CLIP-ViT-bigG-14-laion2B-39B-b160k missing) HOT 1
- [2024-02-19 17:47:19,003]::[InvokeAI]::WARNING --> Failed to get graph state for 6bc4c6f8-f70d-451d-98e0-3fb05387d4e5.[bug]: HOT 2
- [enhancement]: Patch/Healing Brush tool for Unified Canvas
- [enhancement]: Support Download Name & Location for Bulk Downloads HOT 5
- [bug]: AMD HIP out of memory when generating more than one image at 1280x720 HOT 5
- [enhancement]: A toggle button for disable/enable all concepts/controlnet/ip dapter/t2i adapter which are using
- [enhancement]: Improve Context in Outpainting
- [enhancement]: The ControlNet preview should accurately display the image as it will be sent to AI model when ControlNet is set to crop or resize the input image. HOT 4
- [bug]: Torch not compiled with CUDA enabled HOT 2
- [enhancement]: Add option to crop & resize images in Invoke's gallery.
- [enhancement]: Metadata should support multi-image IP adapters
- Update fails with [WinError 5] Access is denied HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from invokeai.