Skip to content

olaviinha/NeuralTextToImage

Repository files navigation

Colab notebooks for text-to-image generators

❗️ This repository is not maintained since 2022, as closed-source state-of-the-art text-to-image solutions are now widely available for everyone.

User-friendly Colab notebooks for various text prompt steered synthetic image generators. These notebooks are not actively maintained, though issues and pull requests are welcome.

Available notebooks (latest to oldest):


These techniques are all more or less descendants of Big Sleep (2021), the original concept of turning text into imagery by using CLIP (OpenAI) to steer BigGAN (Andrew Brock et al.), as introduced by Ryan Murdock in his original notebook. The technique has since branched and evolved into what we now know as Midjourney, Dall-E, Stable Diffusion, etc.

The point of this repository is to record the development history of image-generation AIs, and as long as they work, user-friendly and quick-to-run UIs for the different implementations. Some additional basic features have been added to some of the notebooks, such as saving all/selected progression images, saving progression video, batch processing, etc.

I do not use these notebooks on a regular basis, and hence I'm mostly unaware when some library gets updated and a notebook may no longer function; Please do raise an issue should any problems occur.


Stable Diffusion by CompVis, Stability AI and LAION

This colab requires registering with Hugging Face for login token and accepting model card terms to download required models here and here.

Open In Colab

image

"Satanism in the 1900s"


DALL·E Mini (craiyon.ai) by Boris Dayma

This colab requires registering with wandb for an authentication key to download required models.

Open In Colab

image

"Satanism in the 1900s"


Latent Diffusion LAION 400M by CompVis

Open In Colab

image

"Satanism in the 1900s" (upscaled)


ruDALLE Malevich by Sberbank-AI

Open In Colab

image
"Satanism in the 1900s"


JAX CLIP Guided Diffusion by nshepperd

Method originally by Katherine Crowson

Open In Colab

image
300 iterations of "Satanism in the 1900s".


CLIP+VQGAN by Katherine Crowson

Papers: 1) VQGAN by Patrick Esser et al, 2) CLIP by OpenAI

Open In Colab

image
400 iterations of "Satanism in the 1900s".


Latent Vision by Ryan Murdock

Papers: 1) VQGAN by Patrick Esser et al, 2) CLIP by OpenAI

Open In Colab

image
400 iterations of "Satanism in the 1900s".


Big Sleep by Phil Wang (more precisely this fork)

Papers: 1) BigGAN by Andrew Brock et al, 2) CLIP by OpenAI

Original Big Sleep method.

Open In Colab

image
400 iterations of "Satanism in the 1900s".