OpenAI has recently introduced a new feature to its ChatGPT platform, allowing users to directly edit images generated within the chatbot. The announcement was made on OpenAI’s social network account, X. Users of GPT-4 powered ChatGPT can now click on the generated images and use a paintbrush-style tool to highlight sections they want to adjust or add to.
In a video demonstrating the capabilities of the new feature, a user generates images of a dog wearing a party hat. The user then expands the image and enters an editor view where they can select a paintbrush icon and brush over portions of the dog’s head. By typing in a new prompt, “add bows,” the original image is preserved while a new version is generated with red bows appearing in the user-highlighted region. This enhancement provides users with more control and customization options for the images generated by ChatGPT.
Some web users have already noticed these changes being quietly pushed live earlier in the week. VentureBeat tried out the new feature on a personal account and confirmed that it works as described.
OpenAI’s image generation feature in ChatGPT is powered by its DALL-E 3 model, which was unveiled by the company in September 2023. The integration of DALL-E 3 into ChatGPT has significantly expanded its capabilities for users. The latest addition further enhances the utility and fine-grained control available to users.
Additionally, OpenAI has added a new style inspiration feature in DALL-E 3 GPT. Users can now choose from several pre-set styles such as woodcut, close-up, low angle, artificial lighting, and hand-drawn to further enhance their generated images.
However, these advancements come amidst ongoing legal challenges to OpenAI’s models and growing pushback from some artists and web users against AI art. Some criticize models like DALL-E 3 for potentially using copyrighted imagery without permission, consent, or compensation. Despite the controversies, OpenAI continues to innovate and expand the capabilities of its AI models.
In conclusion, OpenAI’s introduction of direct image editing in ChatGPT allows users to have more control over the images generated by the chatbot. The integration of DALL-E 3 and the new style inspiration feature further enhance the model’s capabilities. While facing legal challenges and criticism, OpenAI remains committed to pushing the boundaries of AI technology.