OpenAI adds GIF generation and editing to ChatGPT
Users can now turn text prompts or photos into custom animated GIFs using the new Images 2.6 update.

The short version
- Images 2.6 was released on Nov. 4, 2026, for ChatGPT, Codex, and the API.
- Users can generate GIFs from text prompts, uploaded photos, or minimal sketches.
- New editing tools allow for speed adjustments and frame-by-frame markups.
- The update reportedly generates images about 50 percent faster than the previous version.
Why it matters
This move shifts GIF creation from searching for existing clips to generating bespoke content for personal use. It gives users more control over visual storytelling in group chats and social media.
Custom animation for everyone
OpenAI has introduced a new way for users to create and modify animated images. By rolling out Images 2.6, the company now allows people to generate GIFs using simple text prompts or existing photos. This update is available to everyone through ChatGPT and Codex, though the number of generations allowed depends on your subscription status.
The new feature addresses the limitations of relying on standard, overused clips from movies or television shows. Instead of searching for the perfect reaction, users can now bring specific ideas to life. This includes turning unique thoughts into animated images that can be shared with friends or posted online.
As Engadget reported, the update was officially released on Nov. 4, 2026. It integrates directly into the existing workflow of the ChatGPT interface, making it easy for non-technical users to experiment with motion. The goal is to provide a more personalized way to communicate visual humor and reactions.
From sketches to motion
The tool offers several different starting points for creating a GIF. Users can type a description, such as a cat yawning, or upload a photo to serve as the base. Even a minimal sketch of an object, like an owl, can be used as a foundation for the AI to build an animation.
One of the more advanced features for creators is the ability to save and tag these inputs as reference images. This allows users to maintain consistency when creating characters, pets, or specific people across different projects. By establishing these references, the AI can better replicate specific visual styles or subjects in future generations.
For developers using the API, the update provides even more granular control over the output. They can choose between two different modes: Flare and Sunburst. These options allow developers to decide the balance between how fast, detailed, and consistent they need their image generation to be for their specific applications.
Precision editing tools
Once a GIF is generated, OpenAI provides several ways to tweak the final result before downloading it. Users can adjust the playback speed by clicking a number, such as 1x, located in the bottom left of the image. This allows the animation to loop faster or slower depending on the desired effect.
If a user wants to change the actual content of the animation, they can use a specific edit button. Clicking this opens a box where the user can describe the changes they want to see. This allows for iterative refining of the GIF until it matches the user's vision perfectly.
For those who need even more control, a new Sheet view has been added to the interface. This view displays the individual frames of the GIF, allowing users to make comments and markups on specific parts of the sequence. This level of detail provides a bridge between automated generation and manual animation techniques.
Performance and scale
OpenAI has made significant technical improvements to the underlying model to ensure a smoother experience. According to the company's blog post, Images 2.6 is designed to generate images about 50 percent faster than the previous version. This speed increase is important for maintaining a fluid experience when users are experimenting with multiple prompts.
The scale of image generation at OpenAI is already massive, with the company reporting that people generate more than 500 million images each day on average. While it is currently unknown how many of those daily images will become GIFs, the tool provides a clear path for that growth.
By making these tools available to the general public, OpenAI is positioning itself as a primary platform for personal content creation. The integration of faster speeds and more intuitive editing options makes it easier for casual users to produce high-quality animations without needing specialized software.
What to watch
- How many users will adopt GIF generation compared to standard image generation?
- Whether OpenAI will introduce more complex animation styles or longer sequences in future updates.
Try it
Log in to ChatGPT and try uploading a simple sketch of an animal to see how the AI turns it into a GIF.
Sources and links
- OfficialOpenAI rolled out Images 2.6 openai.com
- ReportingEngadget: the article we sourced
Liked it? Say why
Add a line for other readers.
No account needed. We never show your email. Comments with links, ads or abuse are held and not shown. Your comment shows after a quick check.
Listen to the AI Wire headlines
Listen to the AI WireListen to our daily AI shows every morning: on your commute, in the shower, wherever you are
Listen to the daily showsFirst reported by Engadget · Read the original. Written by the SI Agent News Desk from the reporting above.Written with AI from the source above. Every number is checked against the source. Spot a mistake? Corrections.
