Recraft, the startup behind a mysterious image model that beat OpenAI’s DALL-E and Midjourney on a respected industry benchmark last year, has raised a $30 million Series B round led by Accel, it exclusively told TechCrunch.  Other investors in the round include Khosla Ventures and Madrona. Based in San Francisco, Recraft previously raised a $12 […]

The arrival of OpenAI's DALL-E 2 in the spring of 2022 marked a turning point in AI, when text-to-image generation suddenly became accessible to a select group of users, creating a community of digital explorers who experienced wonder and controversy as the technology automated the act of visual creation.

But like many early AI systems, DALL-E 2 struggled with consistent text rendering, often producing garbled words and phrases within images. It also had limitations in following complex prompts with multiple elements, sometimes missing key details or misinterpreting instructions. These shortcomings left room for improvement that OpenAI would address in subsequent iterations, such as DALL-E 3 in 2023.

On Tuesday, OpenAI announced new multimodal image-generation capabilities that are directly integrated into its GPT-4o AI language model, making it the default image generator within the ChatGPT interface. The integration, called "4o Image Generation" (which we'll call "4o IG" for short), allows the model to follow prompts more accurately (with better text rendering than DALL-E 3) and respond to chat context for image modification instructions.

Read full article

Comments

© OpenAI

During a livestream on Tuesday, OpenAI CEO Sam Altman announced the first major upgrade to ChatGPT’s image-generation capabilities in over a year. ChatGPT can now leverage the company’s GPT-4o model to natively create and modify images and photos. GPT-4o has long underpinned the AI-powered chatbot platform, but until now, the model has been able to […]

DeepSeek, the viral AI company, has released a new set of multimodal AI models that it claims can outperform OpenAI’s DALL-E 3. The models, which are available for download from the AI dev platform Hugging Face, are part of a new model family that DeepSeek is calling Janus-Pro. They range in size from 1 billion […]

© 2024 TechCrunch. All rights reserved. For personal use only.

Ahead of the holidays, Microsoft said it was upgrading the AI model behind Bing Image Creator, the AI-powered image editing tool built into the company’s Bing search engine. Microsoft promised that the new model — the latest version of OpenAI’s DALL-E 3 model, code-named PR16 — would allow users to create images “twice as fast […]

© 2024 TechCrunch. All rights reserved. For personal use only.

Google DeepMind, Google’s flagship AI research lab, wants to beat OpenAI at the video-generation game — and it might just, at least for a little while. On Monday, DeepMind announced Veo 2, a next-gen video-generating AI and the successor to Veo, which powers a growing number of products across Google’s portfolio. Veo 2 can create […]

© 2024 TechCrunch. All rights reserved. For personal use only.

X, the Elon Musk-owned social network previously known as Twitter, quietly added a new image generator to its Grok assistant this past Saturday. Then, it removed it. Now, it’s bringing it back — and officially announcing it. The image generator, called Aurora, was developed by Musk’s AI company, xAI, and trained on billions of examples from the […]

© 2024 TechCrunch. All rights reserved. For personal use only.

X, the Elon Musk-owned social network previously known as Twitter, has added a new image generator to its Grok assistant. However, after going live for a few hours on Saturday, the product seemed to disappear for some users. Just like the first image generator X added to Grok in October, this one, called Aurora, appears […]

© 2024 TechCrunch. All rights reserved. For personal use only.