ChatGPT Images 2.6 can turn a prompt or photo into a looping GIF
OpenAI's image maker now makes GIFs and remembers your reference photos, and two new developer models arrive in the API.
The short version
- ChatGPT Images 2.6 can turn a prompt or an image into an animated GIF.
- You can adjust GIF speed, edit individual frames and share the result.
- Reference images of you, pets or characters can be saved and reused.
- Developers get GPT-Image-2.6 Flare and Sunburst in the API.
- Flare can generate images in as little as six seconds.
Why it matters
Making a short looping clip or a consistent set of pictures no longer needs separate design tools or repeated uploads. For small businesses, students and creators, that cuts the work of keeping a visual style steady. The price was not stated in the announcement, so check before relying on it for work.
What OpenAI announced
OpenAI introduced ChatGPT Images 2.6, an upgrade to the image maker inside ChatGPT, as community.openai.com reported on its own forum. The two headline additions are GIFs and reusable reference images.
A GIF is a short, looping animated clip, the kind often sent in group chats. A reference image is a photo you hand the AI to use as a guide for what it creates.
GIFs and saved references
You can now turn a prompt or an existing image into an animated GIF. OpenAI says you can change its speed, edit individual frames and share it so it plays on repeat.
Reference images are about not starting over. You save a picture once, such as yourself, a pet or a character, and use it again in new creations without uploading it each time.
The post also mentions image markup and SVG exports. SVG is a image format that stays sharp at any size, which gives you more ways to refine and reuse your work.
Two new models for developers
Developers get two new image models through the API, which is the connection that lets other apps use an AI model. They are called GPT-Image-2.6 Flare and Sunburst.
- Flare is built for speed and can make images in as little as six seconds.
- Sunburst aims for higher quality and more consistency across edits.
OpenAI says the release brings 50% faster image generation overall. Model cards, which are documents describing each model, are linked from the post.
Who this helps
The clearest winners are people who make pictures as part of their work. A shop owner could animate one product photo for a sale post. A creator could keep one reference photo so a run of posts looks consistent.
The announcement is short, so details such as pricing and limits are not in it.
What to watch
- What the new models cost for developers in the API.
- How well saved reference images keep a character looking the same across new creations.
Try it
Open ChatGPT, save a photo of a product or character as a reference image, then ask for a short looping GIF and adjust its speed.
Sources and links
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 community.openai.com · 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.