ChatGPT Sketch
OpenAI's draw-to-image feature — sketch a rough guide in ChatGPT with @Sketch and the model renders it into a detailed, composition-controlled image.
Last verified · 2026-10-23 · by Moe Ameen
Published 2026-09-08 · Updated
Short answer
ChatGPT Sketch is a feature in ChatGPT Images 2.5 that turns a rough drawing into a finished image. Type @Sketch, doodle the layout you want, add a short style description, and the model uses your drawing as a guide for composition. OpenAI launched it on September 8, 2026 for ChatGPT, ChatGPT Work, and Codex users on every tier. You don't need to draw well.
Key takeaways
- Type @Sketch in ChatGPT, draw a rough layout, describe the style, and get a finished image.
- It treats your drawing as a guide for where things go, not something to trace.
- It shipped with Images 2.5 on September 8, 2026, on every ChatGPT tier.
- Sketch steers one image; captions, series, and publishing are on you.
What is ChatGPT Sketch?
ChatGPT Sketch is a feature inside ChatGPT Images 2.5, OpenAI's image model announced September 8, 2026, that lets you draw a rough guide directly in the chat and turn it into a detailed image. You invoke it by typing @Sketch, which opens a drawing canvas; you doodle the layout you want — the shape of a room, the outline of an outfit, how objects sit in a frame — and add a text description of the style and details.
The model treats the drawing as a compositional reference, not a literal image to trace, so a crude scribble is enough to steer where things land.
The point of Sketch is control over the one thing text prompts handle worst: composition. Describing content and style in words is easy; pinning down placement and framing is not. A rough drawing communicates layout in a single gesture, so you get the framing you had in mind without prompt tricks or a dozen retries. OpenAI's framing is that you do not need to be an artist — the sketch is just a faster way to say where everything goes.
Sketch shipped alongside the rest of Images 2.5: Templates (prebuilt starting points for formats like posters and merch), the ability to comment directly on a generated image for focused edits, and up to 50% faster generation than Images 2.0. It rolled out to all ChatGPT, ChatGPT Work, and Codex users across desktop, mobile, and web.
The boundary worth planning around: Sketch is an input to one image, not a content workflow. It steers a single generation and stops there — it does not caption for social, turn one image into a branded multi-format set, keep a persona's face consistent across posts, or publish anywhere.
What can you make with ChatGPT Sketch?
- Composition-controlled images where you draw the layout instead of describing it
- Thumbnail and hero-image concepts with the framing sketched in first
- Product and scene mockups with objects placed exactly where you rough them out
- Outfit, room, or set layouts guided by a quick contour drawing
- Fast iterations on a frame — re-sketch the guide and regenerate to move elements
- Polished renders from crude input, riding ChatGPT Images 2.5's image quality
How do ChatGPT Sketch and Kompozy work together?
Sketch removes the guesswork on the input side of one image; Kompozy removes the grind on the output side of a whole content calendar — and the two chain together cleanly. Say you sketch the composition for a launch graphic, describe the style, and let ChatGPT render it. That is a finished image and an unfinished post. Bring it into Kompozy and it becomes the base asset for a coordinated drop: a brand-exact Carousel built with HyperFrames, a Quote Graphic pulling the headline, and Photo Posts with per-platform copy written in your own voice through the Persona Brief — each reframed for its destination and scheduled across nine platforms plus blog and email with autopilot and a review step.
The complementary strength is worth naming precisely. Sketch controls the layout of a single image, once; Kompozy makes layout and identity repeatable across everything. HyperFrames stamps your exact brand template onto every output, and face-locked Persona Photos keep the same persona face on every render, so a series looks like one brand rather than a set of one-off generations. So the division of labor is clean: use Sketch to nail the composition of the individual image, and use Kompozy to turn that image into a consistent, published presence across every platform. For the wider model Sketch lives in, see our ChatGPT Images 2.5 overview.
- In ChatGPT, type @Sketch, draw the composition you want, and describe the style — then refine the render with a comment or two.
- Bring the finished image into Kompozy as the base asset.
- Fan it into a branded set: a HyperFrames carousel, a quote graphic, and Photo Posts with per-platform copy in your Persona Brief voice.
- For recurring people, generate face-locked Persona Photos in Kompozy so the same face carries across the whole series.
- Reframe each output per platform, then schedule and publish across nine platforms plus blog and email on autopilot.
What does this look like in Kompozy?
A real photo post made in the Kompozy workspace. It's the kind of single-image post a Sketch render can be built into, with copy written for each platform.
Who is this for, and who should skip it?
Best for:
- Creators who know the layout they want but can't get it from a text prompt
- Thumbnail and hero-image work where placement matters more than style
- Non-designers who can scribble a rough guide
Not ideal for:
- Exact technical drawings. The model reinterprets your sketch
- Keeping the same face across a month of posts. Sketch steers one image at a time
- Anyone who needs finished posts. It doesn't caption, schedule, or publish
Frequently asked questions
What is ChatGPT Sketch?
It is a feature in ChatGPT Images 2.5 that turns a rough drawing into a detailed image. You type @Sketch, draw a rough guide for the layout, add a text description of the style, and the model renders a finished image using your sketch as a compositional reference. It launched September 8, 2026.
How do you use the @Sketch feature?
Type @Sketch in ChatGPT to open a drawing canvas, sketch the rough layout you want — a room, an outfit shape, a scene arrangement — and describe the style and details in text. The model uses the drawing as a guide for composition rather than a literal image. You do not need drawing skill; a crude scribble is enough to steer placement.
Does Sketch copy my drawing exactly?
No. It reads the sketch as a compositional reference, not a literal trace, so the model reinterprets it into a detailed render. That is ideal for communicating framing and placement, but exact, dense layouts can drift and usually need a text description to disambiguate.
How do I turn a Sketch image into social media posts?
Generate the composition-controlled image in ChatGPT, then use a content engine to distribute it. On its own Sketch makes one image and stops. In Kompozy you fan that image into a branded carousel, quote graphic, and Photo Posts, add per-platform captions in your voice, and schedule them across nine platforms — the steps Sketch does not do.
Is ChatGPT Sketch free?
It rolled out with ChatGPT Images 2.5 to ChatGPT, ChatGPT Work, and Codex users on every tier, Free included. OpenAI's pricing page lists limited image creation on Free, more on Go and Plus, and unlimited, faster image creation on Pro, so check current limits there.
How do we know this?
We checked every figure, date, and price on this page against the sources listed below on 2026-10-23, including OpenAI's Images 2.5 announcement and the ChatGPT pricing page as rendered in a browser. Kompozy plan, format, and platform details come from kompozy.io and kompozy.io/pricing.
Sources
- OpenAI — Introducing ChatGPT Images 2.5 (read 2026-10-23)
- OpenAI — ChatGPT plans and pricing (read 2026-10-23)
- Kompozy — Home (platforms, formats, Persona Brief, autopilot) (read 2026-10-23)
- Kompozy — Pricing (plans, credits, 9 platforms, output formats) (read 2026-10-23)
Related tools
- ChatGPT Images 2.5 — OpenAI's new state-of-the-art image model — faster generation, in-chat Sketch and Templates, and two API models (GPT-Image-2.5 Flare and Sunburst).
- ChatGPT Video Generation — The honest state of making video with ChatGPT in 2026: it writes scripts, shot lists, and render prompts and generates stills — but it renders no video, and OpenAI's Sora video model is being shut down.
- Google Pics — Google's prompt-first AI image generator and editor inside Google Workspace — describe a design in words instead of building it from a template, powered by the Nano Banana model.
- DaVinci Resolve 21.1 — Blackmagic Design's pro editor, now with a native MCP server that lets AI assistants like Claude and ChatGPT drive Resolve Studio by natural-language command.
- ChatGPT Pro — OpenAI's top individual ChatGPT plan — $200/month for the highest message limits and priority access to its most advanced models and tools.