vqgan-clip

For automating the creation of large batches of AI-generated artwork locally.

Getting the latest versions of Disco Diffusion to work locally, instead of colab. Including how I run this on Windows, despite some Linux only dependencies ;)

Multiple notebooks which allow the use of various machine learning methods to generate or modify multimedia content

Implements VQGAN+CLIP for image and video generation, and style transfers, based on text and image prompts. Emphasis on ease-of-use, documentation, and smooth video creation.

Start here

Local image generation using VQGAN-CLIP or CLIP guided diffusion

A simple library that implements CLIP guided loss in PyTorch.

Based on the Disco Diffusion, we have developed a Chinese & English version of the AI art creation software "AI Atelier". We offer both Text-To-Image models (Disco Diffusion and VQGAN+CLIP) and Text-To-Text (GPT-J-6B and GPT-NEOX-20B) as options. 在Disco Diffusion模型的基础上，我们开发了一款汉化版AI艺术创作软件“AI聊天画室”。我们同时提供了文本生成图像模型（Disco Diffusion与VQGAN+CLIP）及文本生成文本（GPT-J-6B及GPT-NEOX-20B）可供选择。

Streamlit Tutorial (ex: stock price dashboard, cartoon-stylegan, vqgan-clip, stylemixing, styleclip, sefa)

Generates a random prompt for a VQGAN+CLIP

Traditional deepdream with VQGAN+CLIP and optical flow. Ready to use in Google Colab.

Art generation using VQGAN + CLIP using docker containers. A simplified, updated, and expanded upon version of Kevin Costa's work. This project tries to make generating art as easy as possible for anyone with a GPU by providing a simple web UI.

ArtAI is an interactive art installation that collects people's ideas in real-time from social media and uses deep learning and AI art generation to curate these ideas into a dynamic display.

The purpose of the project is to understand a basic GAN from scratch. A WGAN was built to generate people's faces based in the Celeba Dataset. VQGAN + CLIP model was used to generate unique designs that would be used in fashion.

Gradio Web app for running VQGAN-CLIP locally

creates item images utilizing procgen and neural networks

AI-powered art generator based on VQGAN+CLIP

creates ability icon images utilizing procgen and neural networks

Mozart - A Generative Art Platform

VQGAN and CLIP are actually two separate machine learning algorithms that can be used together to generate images based on a text prompt. VQGAN is a generative adversarial neural network that is good at generating images that look similar to others (but not from a prompt), and CLIP is another neural network that is able to determine how well a caption (or prompt) matches an image.