#130 · Primary category： Image Generation
deep-daze
Simple command line tool for text to image generation using OpenAI's CLIP and Siren (Implicit neural representation network). Technique was originally created by https://twitter.com/advadnoun
Project last updated：03/13/22
GitHub Stars
4.3K
Forks
309
Contributors
14
License
MIT
Why we included this project
Deep Daze was one of the earliest practical demonstrations of CLIP-guided text-to-image generation, a technique Ryan Murdock discovered and Lucidrains packaged as a command line tool. You give it a phrase like "imagine a house in the forest" and it steers a SIREN network, using OpenAI's CLIP, until the rendered image matches your prompt. It is a hands-on way to learn how prompt-guided synthesis actually works, helped along by Colab notebooks and a --deeper flag for higher quality output. You will want an Nvidia or AMD GPU with at least 4GB of VRAM. It is dated next to modern generators, but as a teaching tool for the foundations of this field it still has value.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
stable-diffusion-webui
Stable Diffusion web UI
ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
diffusers
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
upscayl
🆙 Upscayl - #1 Free and Open Source AI Image Upscaler for Linux, MacOS and Windows.
InvokeAI
InvokeAI is a leading open-source creative engine for Stable Diffusion, offering an industry-leading web UI for generating and editing visual media.