ChatGPT is getting a new feature that could make GIF creation easier. OpenAI has introduced Images 2.6, its latest image-generation model, which brings native GIF creation to the platform. Users can now upload a photograph, describe the animation they want and turn a static image into a moving GIF.
The update also offers faster image generation and greater creative control. Users can modify animation speeds, edit individual frames and share their completed GIFs directly through ChatGPT.
Here's a closer look at how the feature works and the other improvements included in Images 2.6.
How to create GIFs using ChatGPT
Creating a GIF with ChatGPT is straightforward. Users need to open the platform, upload a photograph of themselves, their pets or another subject, and describe the animation they want.
GIFs can also be generated entirely through text prompts without uploading any images.
OpenAI suggests using a prompt such as: "Animate me peeking over a mountain of Diwali gift boxes. Playful cartoon style, looping GIF."
After the GIF is generated, users can customise the animation. Images 2.6 allows playback speeds ranging from 0.5x to 2x and provides the option to edit individual frames.
Existing editing tools can also be used to resize elements or remove unwanted objects. This gives users the flexibility to refine their animations rather than accepting the initial output.
What else is new with Images 2.6?
GIF creation is not the only major addition to the new image-generation model. Images 2.6 also brings faster image generation and a feature that allows users to save and tag reference images of people, pets and characters.
With this capability, users can reuse familiar faces or characters in future creations without having to upload the same reference photograph repeatedly.
OpenAI revealed that users now generate more than 4 billion images every week across ChatGPT and its API. This represents an increase from the over 3 billion images reported eight weeks earlier, when Images 2.5 was introduced.
For developers, OpenAI has launched GPT-Image-2.6 Flare and Sunburst through its API. The company claims that these models can generate images 50 per cent faster.
Flare is designed for faster image creation and can produce images in as little as six seconds at low quality. Sunburst, meanwhile, prioritises higher-quality outputs and improved consistency across edits at medium or high quality.
Images 2.6 availability in India
Images 2.6 is available to all ChatGPT users, including those on the free plan. The feature can be accessed through the web, desktop and mobile applications.
It is also available through ChatGPT Work and Codex, allowing users to experiment with GIF creation and image editing across different environments.
Developers can access GPT-Image-2.6 Flare and Sunburst through OpenAI's API. Users in India can also explore the new GIF-generation and image-editing capabilities directly within ChatGPT.
