US EditionChatGPT Images 2: Why OpenAI Built a New Image Model After Killing Sora
The new model can create multiple images from one prompt and render readable text in Chinese and Hindi, OpenAI said.
- On Tuesday, OpenAI launched ChatGPT Images 2.0, an AI-powered image generator featuring 'Thinking' capabilities, 2K resolution, and improved text rendering for more sophisticated image creation.
- OpenAI developed the model to address the 'intent gap' plaguing AI art, shifting from a simple 'tool' to a 'visual system' capable of reasoning through image structure and layout.
- With 'Thinking' capabilities, the model searches the web and reasons through layouts before rendering, generating up to eight distinct images with 'character and object continuity' while making 'significant gains' in Japanese and Korean text rendering.
- All ChatGPT and Codex users gain immediate access to the base model, while advanced 'Thinking' features remain reserved for paid subscribers; developers can integrate the gpt-image-2 API supporting resolutions up to 4K.
- Amid recent reports of AI-generated characters used in political campaigns, OpenAI emphasizes safety protocols including watermarking and real-time monitoring to prevent election interference and ensure the technology serves 'economically valuable creative tasks.
55 Articles
55 Articles
OpenAI announced the release of ChatGPT Images 2.0, a new artificial intelligence (AI) image model that stands out for its superior precision and the inclusion of visual reasoning capabilities. ChatGPT...
The new model promises not only unprecedented photorealism but also the ability to create complex visual content. OpenAI announced the release of Images 2.0, calling it a "renaissance" of digital art. The new tool, built directly into ChatGPT, offers two operating modes: the fast Instant mode and the intelligent Thinking mode, according to RBC-Ukraine, citing Gizmodo. More interesting: From TV series to AI chats: the top 10 apps for learning for…
OpenAI wants you to know how good its new image model is at faking real photos
ChatGPT Images 2.0 can crawl the internet to create mockups of magazines, manga, and other creative work.Courtesy OpenAIOpenAI released ChatGPT Images 2.0, a new image generator, on Thursday.The company teased the model by showing a fake screenshot.ChatGPT Images 2.0 can also generate images based on prompts written in other languages.OpenAI wants you to know how good its latest image generator is —and it has a few fake screenshots and pictures …
With the launch of ChatGPT Images 2.0, OpenAI now "thinks" before it draws
OpenAI has launched ChatGPT Images 2.0, positioning its new image model as a shift from a rendering tool to what the company calls a “visual thought partner.” This “partner,” which debuted on Tuesday, is a system capable of reasoning through complex visual tasks, verifying its own outputs, and generating up to eight coherent images from a single prompt. The model, available via the API as gpt-image-2, is rolling out to all ChatGPT and Codex user…
Two years ago, by asking an image generator to draw a letter from a Mexican restaurant, the AI returned invented dishes like an "enchuita" or a...
Coverage Details
Bias Distribution
- 47% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
