Skip to content

Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

License

Notifications You must be signed in to change notification settings

meet1919/visual-chatgpt

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

66 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Visual ChatGPT

Visual ChatGPT connects ChatGPT and a series of Visual Foundation Models to enable sending and receiving images during chatting.

See our paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

Open in Spaces Open in Colab

Updates:

  • We propose the template idea in Visual ChatGPT!
    • A template is a pre-defined execution flow that assists ChatGPT in assembling complex tasks involving multiple foundation models.
    • A template contains the experiential solution to complex tasks as determined by humans.
    • A template can invoke multiple foundation models or even establish a new ChatGPT session
    • To define a template, simply adding a class with attributes template_model = True
  • Thanks to @ShengmingYin and @thebestannie for providing a template example in InfinityOutPainting class (see the following gif)
    • Firstly, run python visual_chatgpt.py --load "ImageCaptioning_cuda:0,ImageEditing_cuda:1,VisualQuestionAnswering_cuda:2"
    • Secondly, say extend the image to 2048x1024 to Visual ChatGPT!
    • By simply creating an InfinityOutPainting template, Visual ChatGPT can seamlessly extend images to any size through collaboration with existing ImageCaptioning, ImageEditing, and VisualQuestionAnswering foundation models, without the need for additional training.
  • Visual ChatGPT needs the effort of the community! We crave your contribution to add new and interesting features!

Insight & Goal:

On the one hand, ChatGPT (or LLMs) serves as a general interface that provides a broad and diverse understanding of a wide range of topics. On the other hand, Foundation Models serve as domain experts by providing deep knowledge in specific domains. By leveraging both general and deep knowledge, we aim at building an AI that is capable of handling various tasks.

Demo

System Architecture

Logo

Quick Start

# clone the repo
git clone https://github.com/microsoft/visual-chatgpt.git

# Go to directory
cd visual-chatgpt

# create a new environment
conda create -n visgpt python=3.8

# activate the new environment
conda activate visgpt

#  prepare the basic environments
pip install -r requirements.txt

# prepare your private OpenAI key (for Linux)
export OPENAI_API_KEY={Your_Private_Openai_Key}

# prepare your private OpenAI key (for Windows)
set OPENAI_API_KEY={Your_Private_Openai_Key}

# Start Visual ChatGPT !
# You can specify the GPU/CPU assignment by "--load", the parameter indicates which 
# Visual Foundation Model to use and where it will be loaded to
# The model and device are separated by underline '_', the different models are separated by comma ','
# The available Visual Foundation Models can be found in the following table
# For example, if you want to load ImageCaptioning to cpu and Text2Image to cuda:0
# You can use: "ImageCaptioning_cpu,Text2Image_cuda:0"

# Advice for CPU Users
python visual_chatgpt.py --load ImageCaptioning_cpu,Text2Image_cpu

# Advice for 1 Tesla T4 15GB  (Google Colab)                       
python visual_chatgpt.py --load "ImageCaptioning_cuda:0,Text2Image_cuda:0"
                                
# Advice for 4 Tesla V100 32GB                            
python visual_chatgpt.py --load "ImageCaptioning_cuda:0,ImageEditing_cuda:0,
    Text2Image_cuda:1,Image2Canny_cpu,CannyText2Image_cuda:1,
    Image2Depth_cpu,DepthText2Image_cuda:1,VisualQuestionAnswering_cuda:2,
    InstructPix2Pix_cuda:2,Image2Scribble_cpu,ScribbleText2Image_cuda:2,
    Image2Seg_cpu,SegText2Image_cuda:2,Image2Pose_cpu,PoseText2Image_cuda:2,
    Image2Hed_cpu,HedText2Image_cuda:3,Image2Normal_cpu,
    NormalText2Image_cuda:3,Image2Line_cpu,LineText2Image_cuda:3"
                             

GPU memory usage

Here we list the GPU memory usage of each visual foundation model, you can specify which one you like:

Foundation Model GPU Memory (MB)
ImageEditing 3981
InstructPix2Pix 2827
Text2Image 3385
ImageCaptioning 1209
Image2Canny 0
CannyText2Image 3531
Image2Line 0
LineText2Image 3529
Image2Hed 0
HedText2Image 3529
Image2Scribble 0
ScribbleText2Image 3531
Image2Pose 0
PoseText2Image 3529
Image2Seg 919
SegText2Image 3529
Image2Depth 0
DepthText2Image 3531
Image2Normal 0
NormalText2Image 3529
VisualQuestionAnswering 1495

Acknowledgement

We appreciate the open source of the following projects:

Hugging FaceLangChainStable DiffusionControlNetInstructPix2PixCLIPSegBLIP

Contact Information

For help or issues using the Visual ChatGPT, please submit a GitHub issue.

For other communications, please contact Chenfei WU ([email protected]) or Nan DUAN ([email protected]).

About

Official repo for the paper: Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%