--- title: ChatGPT adds GIF creation and editing with Images 2.6 description: ChatGPT can now generate and edit animated GIFs with a new image model called Images 2.6. You can type a prompt like 'a dancing cat GIF' or upload a photo to... canonical: https://daily.dev/posts/chatgpt-adds-gif-creation-and-editing-with-images-2-6-rzmja7sbl twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: ChatGPT adds GIF creation and editing with Images 2.6 | daily.dev og:description: ChatGPT can now generate and edit animated GIFs with a new image model called Images 2.6. You can type a prompt like 'a dancing cat GIF' or upload a photo to... og:url: https://daily.dev/posts/chatgpt-adds-gif-creation-and-editing-with-images-2-6-rzmja7sbl og:image: https://api.daily.dev/og/posts/rzMja7SBl.png og:image:alt: ChatGPT adds GIF creation and editing with Images 2.6 og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # ChatGPT adds GIF creation and editing with Images 2.6 **[Collections](https://daily.dev/sources/collections)** · 2 min read · 0 upvotes · 0 comments ## Summary ChatGPT can now generate and edit animated GIFs with a new image model called Images 2.6. You can type a prompt like 'a dancing cat GIF' or upload a photo to animate it, then adjust playback speed and edit individual frames. Developers get two new API models: GPT-Image-2.6 Flare, tuned for speed, and GPT-Image-2.6 Sunburst, tuned for quality. OpenAI says people now make more than 4 billion images a week across ChatGPT and its API, up from 3 billion in September. ## Content OpenAI has released Images 2.6, an update to ChatGPT's image generation. It adds GIF creation and reference images, and OpenAI says it generates images 50% faster than before. ## GIFs in ChatGPT ChatGPT can now generate and edit GIFs in a single step. Before this, making an animated GIF took extra steps instead of a direct request. Now you can ask for something like a dancing cat GIF, or turn an uploaded photo into one. After that you can change the playback speed and edit the individual frames the GIF is built from. Images 2.6 is available globally in ChatGPT and Codex across all subscription tiers, on desktop, mobile and web. ## Two new API models Developers get two new image models in Codex and the API: - GPT-Image-2.6 Flare, built for speed - GPT-Image-2.6 Sunburst, built for quality OpenAI says both generate images 50% faster than before. At medium or high quality, Sunburst keeps details more consistent from one edit to the next. The API also gives developers more control over image complexity, and can create GIFs. Pricing for text-to-image and image-to-image is listed at $8 and $5 for input and $30 for output, as reported by @testingcatalog. ## Usage OpenAI says people now make more than 4 billion images a week across ChatGPT and its API, up from 3 billion in September. One thing I'll be watching is how well the frame-level editing holds up in practice. Editing a GIF frame by frame has always been tedious, so if this works as described, it removes a real chore. ## Questions this post answers ### How can I generate an animated GIF using ChatGPT? ChatGPT now supports GIF generation and editing through a new image model called Images 2.6. You simply type a prompt such as 'a dancing cat GIF' or upload a photo to have it animated. Once created, you can adjust the GIF's playback speed and view or edit the individual frames it was built from. _Developers tracking new ChatGPT media features can follow updates like these on daily.dev._ ### What are GPT-Image-2.6 Flare and Sunburst? GPT-Image-2.6 Flare and Sunburst are two new API image models from OpenAI released alongside Images 2.6. Flare is tuned for speed, while Sunburst is tuned for quality, giving developers a choice depending on whether they need fast generation or higher-quality output. _Developers choosing between speed and quality in image APIs can track model releases like this on daily.dev._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 118 comments across hackernews (as of 2026-11-05). **TL;DR:** Reactions to Images 2.6 are mixed: some are impressed by improved prompt adherence and detail (e.g. correctly rendering Pokemon grids), while many find the new GIF feature glitchy, dislike persistent visible watermarking/artifacts, and are frustrated by pricing and rollout inconsistencies. **Sentiment:** 25% positive · 40% mixed · 35% skeptical **The case for** - Some testers found prompt adherence and accuracy notably improved compared to prior models and competitors like Nano Banana Pro. - The new native GIF generation capability is seen as an interesting, if imperfect, new feature. - SVG output support is viewed as a novel and potentially useful addition. **The pushback** - Many found the GIF outputs splotchy, flickery, and not production-ready, calling the feature a 'nonstarter' for serious use. - Visible watermarking/artifacting is still considered worse than competitors like Google's Nano Banana. - Pricing analysis shows token usage (and thus cost) roughly tripled or quadrupled at low/medium quality settings despite OpenAI claiming no price change. - Sharing generated GIFs redirects to ChatGPT.com with a static image instead of the actual GIF, which some called a sleazy engagement pattern. - Several noted codex-cli still uses the older gpt-image-2 model despite claims of availability across Codex. - Some design-focused users found 2.6 performed worse than 2.5 for certain UI/poster use cases. - Persistent 'AI look' aesthetic and slop-like appearance of outputs continues to bother some viewers. - Generating certain content still triggers guardrail refusals inconsistently. **By community** - hackernews (mixed): Opinions split between genuine enthusiasm for improved prompt adherence and SVG support, and frustration over GIF glitches, pricing increases, watermarking, and inconsistent rollout. **Hottest debate:** Whether the new GIF generation feature is a genuinely useful capability or just slop-tier output not worth the hype, with sharp disagreement over how harshly to judge the artifacts. **Open questions** - How exactly does the SVG output pipeline work internally (raster-to-vector conversion)? - Why does token usage roughly triple/quadruple at low/medium quality while pricing per token stays the same? - When will codex-cli actually support the newer gpt-image-2.6 model as claimed? - Is the reported '4 billion images per week' figure accurate or inflated by automated/duplicate generation? **Highlights** > Yes, the Pokemon are correct. Compare to my attempt a year ago with Nano Banana Pro, which plagiarized the images, didn't do interesting things with the background, and got 271 wrong: https://minimaxir.com/2025/12/nano-banana-pro/pokemongrid_hu... When I did a similar prompt with ChatGPT 2.0 it was worse, so interesting to see improvement. > — [minimaxir on hackernews](https://news.ycombinator.com/item?id=50373540) > The splotchiness on that simple chess animation makes this GIF feature a nonstarter. > — [minimaxir on hackernews · 2 comments](https://news.ycombinator.com/item?id=50373729) > The input and output pricing per token remains the same between 2.5 and 2.6, although using their image pricing calculator shows a quadrupling of token usage at low and medium quality settings for 2.6. For e.g. at 1024x1024: 2.5 low, 196 tokens, $0.006 2.6 low, 823 tokens, $0.025 2.5 med, 439 tokens, $0.013 2.6 med, 1449 tokens, $0.043 Interestingly, higher quality settings show no change in token usage between the models. > — [bsboxe on hackernews · 1 comments](https://news.ycombinator.com/item?id=50373444) > On a phone, if you share a gif, it creates a link to ChatGPT.com with a static image. You can also save the image to photos and share directly from there which feels like an unnecessary step. It feels like a sleazy pattern and defeats the purpose of why I’d want to generate a gif in the first place, which to make clear is likely going to be to share with friends in a chat. I’m not interested in driving traffic to ChatGPT.com to impress my friends. > — [speak\_plainly on hackernews · 1 comments](https://news.ycombinator.com/item?id=50373769) > That stained glass whale thing makes me especially grumpy. When it scrolled onto the page, my first thought was "whoah, what a neat idea" and then it was _immediately_ followed by "what a terribly execution." Like, I'm not even an artist, so I'm sure there's a million things I'm missing, but it's just so upsetting to look at. There's weird random reflections on things that shouldn't have reflections, the coloured light absolutely doesn't actually track through the stained glass onto any surface that makes any sense, light is coming from every which way, it's just... gross to look at for anything more than a quarter of a second. And this is what they're using to hype people up for it. /shrug > — [DanHulton on hackernews · 2 comments](https://news.ycombinator.com/item?id=50373586) > Using the grid trick for animations to generate the individual frames has been around for awhile and not specific to ChatGPT: I'm surprised it took this long for one of the official providers to make it explicit. However, adherence between frames is generally tricky, and even in the examples there is a lot of noise between frames although that could be due to compression. SVG support is interesting but I suspect shenanigans are afoot since that's not how image generation models work, and it would likely strip any SynthID watermarks. It's possible OpenAI has pipelined a raster-to-vector tool that does the conversion automatically. (I developed a similar pipeline and it works extremely well; I'll open source it at some point) EDIT: Per documentation, there is an explicit `output_format: "svg"`, and I am indeed correct there is raster-to-vector in play: > The API creates a reference image and uses it to produce the SVG. The quality setting controls that reference image. Decode data[0].b64_json as base64 and save the resulting UTF-8 XML bytes with a .svg extension. OpenAI claims 50% faster generation with Images 2.6 but curiously price is the same as Image 2.5. > — [minimaxir on hackernews](https://news.ycombinator.com/item?id=50373156) **Source threads** - [hackernews](https://news.ycombinator.com/item?id=50372945) · 70 points · 118 comments ## Similar posts on daily.dev - [OpenAI’s new ChatGPT image generator makes faking photos easy](https://daily.dev/posts/openai-s-new-chatgpt-image-generator-makes-faking-photos-easy-kd3sfqwpr) · Ars Technica · 1 upvotes · 0 comments --- Tags: [#openai](https://daily.dev/tags/openai), [#genai](https://daily.dev/tags/genai), [#chatgpt](https://daily.dev/tags/chatgpt) [View this post on daily.dev](https://daily.dev/posts/chatgpt-adds-gif-creation-and-editing-with-images-2-6-rzmja7sbl) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"ChatGPT adds GIF creation and editing with Images 2.6","url":"https://daily.dev/posts/chatgpt-adds-gif-creation-and-editing-with-images-2-6-rzmja7sbl","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/chatgpt-adds-gif-creation-and-editing-with-images-2-6-rzmja7sbl"},"datePublished":"2026-11-04T19:50:21.072Z","dateModified":"2026-11-05T01:44:42.982Z","description":"ChatGPT can now generate and edit animated GIFs with a new image model called Images 2.6. You can type a prompt like 'a dancing cat GIF' or upload a photo to...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9007f3dea2ee5d75c23b7e99120c55ca?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/9007f3dea2ee5d75c23b7e99120c55ca?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/chatgpt-adds-gif-creation-and-editing-with-images-2-6-rzmja7sbl","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"openai,genai,chatgpt","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"ChatGPT adds GIF creation and editing with Images 2.6"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/chatgpt-adds-gif-creation-and-editing-with-images-2-6-rzmja7sbl#faq","mainEntity":[{"@type":"Question","name":"How can I generate an animated GIF using ChatGPT?","acceptedAnswer":{"@type":"Answer","text":"ChatGPT now supports GIF generation and editing through a new image model called Images 2.6. You simply type a prompt such as 'a dancing cat GIF' or upload a photo to have it animated. Once created, you can adjust the GIF's playback speed and view or edit the individual frames it was built from. Developers tracking new ChatGPT media features can follow updates like these on daily.dev."}},{"@type":"Question","name":"What are GPT-Image-2.6 Flare and Sunburst?","acceptedAnswer":{"@type":"Answer","text":"GPT-Image-2.6 Flare and Sunburst are two new API image models from OpenAI released alongside Images 2.6. Flare is tuned for speed, while Sunburst is tuned for quality, giving developers a choice depending on whether they need fast generation or higher-quality output. Developers choosing between speed and quality in image APIs can track model releases like this on daily.dev."}}]} ```