OpenAI has unveiled the latest iteration of its text-to-image tool, DALL-E, DALL-E 3, which features full integration with ChatGPT. It now lets users use ChatGPT to create prompts.
Utilizing ChatGPT streamlines the process for users who don’t want to create detailed prompts themselves to guide DALL-E 3. Instead, they can simply request ChatGPT to generate a prompt, and the chatbot will generate a paragraph (DALL-E performs more effectively with longer sentences) for DALL-E 3 to adhere to. However, users who have specific concepts in mind for DALL-E can still employ their own prompts.
DALL-E was created and introduced by OpenAI in January 2021. It was announced as a research project that showcases the capabilities of AI in generating images from textual descriptions. It is a variation of the GPT-3 (Generative Pre-trained Transformer 3) architecture, which is known for its ability to generate human-like text based on the input it receives. DALL-E, however, is designed specifically for generating images from textual descriptions.
The name “DALL-E” is a portmanteau of the famous surrealist artist Salvador Dalí and the Pixar character Wall-E. DALL-E’s primary function is to generate images from textual prompts. You can give it a description, and it will create an image based on that description. For example, if you ask DALL-E to generate an image of a “giraffe made of ice cream,” it will produce a visual representation of that concept.
DALL-E 3 produces images with a high level of fidelity by meticulously interpreting intricate descriptions, including the generation of text within images, such as labels and signs. This represents a significant improvement over previous models that faced challenges in this aspect.
The initial release of DALL-E 3 is scheduled for October, starting with availability to ChatGPT Plus and ChatGPT Enterprise users. Following this, it will gradually become accessible to research labs and through its API service in the autumn season. OpenAI has outlined plans for a phased release of DALL-E 3 but has not provided a specific timeline for when it will be made available to the general public for free.
