Text-to-image model

A text-to-image model is a machine learning model which takes an input natural language description and produces an image matching that description. Such models began to be developed in the mid-2010s, as a result of advances in deep neural networks. In 2022, the output of state of the art text-to-image models, such as OpenAI's DALL-E 2, Google Brain's , StabilityAI's Stable Diffusion, and Midjourney began to approach the quality of real photographs and human-drawn art. Text-to-image models generally combine a language model, which transforms the input text into a latent representation, and a generative image model, which produces an image conditioned on that representation. The most effective models have generally been trained on massive amounts of image and text data scraped from the web. Before the rise of deep learning, attempts to build text-to-image models were limited to collages by arranging existing component images, such as from a database of clip art. The inverse task, , was more tractable and a number of image captioning deep learning models came prior to the first text-to-image models. The first modern text-to-image model, alignDRAW, was introduced in 2015 by researchers from the University of Toronto. alignDRAW extended the previously-introduced DRAW architecture (which used a recurrent variational autoencoder with an attention mechanism) to be conditioned on text sequences. Images generated by alignDRAW were blurry and not photorealistic, but the model was able to generalize to objects not represented in the training data (such as a red school bus), and appropriately handled novel prompts such as "a stop sign is flying in blue skies", showing that it was not merely "memorizing" data from the training set. In 2016, Reed, Akata, Yan et al. became the first to use generative adversarial networks for the text-to-image task. With models trained on narrow, domain-specific datasets, they were able to generate "visually plausible" images of birds and flowers from text captions like "an all black bird with a distinct thick, rounded bill".

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Related concepts (10)

Related courses (14)

Related lectures (99)

Text-to-image model

Generative pre-trained transformer

Generative pre-trained transformers (GPT) are a type of large language model (LLM) and a prominent framework for generative artificial intelligence. The first GPT was introduced in 2018 by OpenAI. GPT models are artificial neural networks that are based on the transformer architecture, pre-trained on large data sets of unlabelled text, and able to generate novel human-like content. As of 2023, most LLMs have these characteristics and are sometimes referred to broadly as GPTs.

DALL-E

DALL-E (stylized as DALL·E) and DALL-E 2 are s developed by OpenAI using deep learning methodologies to generate s from natural language descriptions, called "prompts". DALL-E was revealed by OpenAI in a blog post in January 2021, and uses a version of GPT-3 modified to generate images. In April 2022, OpenAI announced DALL-E 2, a successor designed to generate more realistic images at higher resolutions that "can combine concepts, attributes, and styles". OpenAI has not released source code for either model.

CS-625: Transfer learning and meta-learning

This seminar course covers principles and recent advancements in machine learning methods that have the ability to solve multiple tasks and generalize to new domains in which training and test distrib

FIN-407: Machine learning in finance

This course aims to give an introduction to the application of machine learning to finance. These techniques gained popularity due to the limitations of traditional financial econometrics methods tack

MICRO-573: Deep learning for optical imaging

This course will focus on the practical implementation of artificial neural networks (ANN) using the open-source TensorFlow machine learning library developed by Google for Python.

Vision-Language-Action Models: Training and Applications

Delves into training and applications of Vision-Language-Action models, emphasizing large language models' role in robotic control and the transfer of web knowledge. Results from experiments and future research directions are highlighted.

Social Image Systems: From Past to Present DH-500: Computational Social Media

Explores the evolution of social image systems, deep learning models, selfies, and biometrics in online platforms.

Neural Networks Optimization CIVIL-459: Deep learning for autonomous vehicles

Explores neural networks optimization, including backpropagation, batch normalization, weight initialization, and hyperparameter search strategies.