(CTN News) – OpenAI has introduced an upgraded version of its text-to-image tool, DALL-E, which leverages ChatGPT, their popular AI chatbot, to simplify the process of generating image prompts.
AI-driven image generation tools currently rely on prompts, which are descriptions of images, to create artwork in various styles, from photorealistic to fantastical. However, crafting the perfect prompt can be a daunting task, leading to the emergence of “prompt engineering” as a specialized profession.
OpenAI’s latest offering, DALL-E 3, incorporates ChatGPT to assist in refining prompts. Subscribers to OpenAI’s premium ChatGPT plans, ChatGPT Plus and ChatGPT Enterprise can now input a request for an image and refine it through conversations with the chatbot, receiving the results directly within the chat application.
ChatGPT can take even short prompts consisting of just a few words and enhance their descriptiveness, providing more detailed guidance to the DALL-E 3 model.
The integration of ChatGPT is not the only enhancement in DALL-E 3. This version is designed to generate higher-quality images that closely align with the provided prompts, particularly when dealing with longer prompts. It also handles challenging content that has historically posed difficulties for image-generating models, such as text and human hands.
Furthermore, DALL-E 3 incorporates new mechanisms to reduce algorithmic bias and enhance safety. For instance, it will reject requests for images in the style of living artists or portraying public figures.
The Future of AI-Generated Visual Content: DALL-E 3’s Impact
Additionally, artists now can opt out of having their artwork used to train future generations of OpenAI text-to-image models.
(It’s worth noting that OpenAI and some of its competitors have faced legal challenges over the alleged use of artists’ copyrighted work in training its generative AI image models.)
The launch of DALL-E 3 amidst intensifying competition in the generative AI field, particularly in image synthesis. Competitors like Midjourney and Stability AI continually refine their image-generating models, putting pressure on OpenAI to maintain its position.
OpenAI plans to introduce DALL-E 3 to premium ChatGPT users in October, with subsequent availability to research labs and API customers. However, there has been no mention of whether or when a free web tool similar to DALL-E 2 and the original DALL-E model will be released.
This development marks a significant step forward in AI-powered image generation and has the potential to reshape how we create and interact with visual content in various applications.