ChatGPT quietly upgrades to GPT-Image-2.5 with new Sketch feature

On September 9, users discovered that ChatGPT's image generation model had quietly been updated to GPT-Image-2.5, with no major official announcement from OpenAI, alongside a new Sketch feature. Community testing concludes the update is a modest but focused improvement: text rendering, local editing, and sketch-to-image are clearly better, while long-standing texture noise issues remain largely unchanged.

Confirmed

• GPT-Image-2.5 is live in ChatGPT, confirmed by multiple users including markk and xiaohu, plus a user test shared via DeryaTR.
• OpenAI shipped Sketch alongside Images 2.5: typing @Sketch in ChatGPT lets users hand-draw a sketch that the AI turns into a finished image; currently web-only, not on desktop. APPSO tested it with a wobbly movie-poster sketch; aitrendzxyz shared a test turning a few irregular lines into polished images across four creative directions; Andrew Mayne (shared by lukaszkaiser) argues such small design-adjustment tools deliver outsized productivity gains.
• markk ran the classic "noise artifact" test (a lush, high-detail forest clearing photo) with mixed results; he concluded noise is no worse but no better—the new version is essentially flat on texture artifacts.
• Text rendering is a clear win: a Japanese designer found text in generated webpage designs no longer garbled, and Ben Geskin produced an "iPhone Duo - Apple Event" slide deck with crisp text.
• xiaohu called the new model "something" and demonstrated precise local edits on infographics without breaking overall layout, plus layout adjustment, with side-by-side comparisons against other models.
• Other tests: ZeroZJQ showed the new model handles the "slumped against a wall" pose that many models fail; GodsBurnt generated a product shot with lighting, equipment, and even the barcode on a graded card; Mayz1169 shared prompts converting any character reference into a 4×4 pixel battle sprite sheet (tested with Tanjiro) and pixel idle animations. aitrendzxyz summarized the three core improvements as sketch-to-image, targeted local editing, and readable text.
• Aizkmusic tested with a character-selection scene, calling it a slight, "half-generation" upgrade whose outputs still visibly look AI-generated—"this is its worst moment," and it will only get better.

Unconfirmed

• ElonBaldMusk complained the patterned noise is "worse than before," conflicting with markk's "no worse but no better" verdict; the artifact verdict remains unsettled.

Why it matters

• Image generation is a core ChatGPT capability, and the "2.5" naming signals incremental iteration rather than a major leap. Community views on artifact fixes are cautious, but Sketch interaction, precise local editing, and reliable text rendering show markedly better controllability over structured graphic content—valuable for UI mockups, slides, and product shots—and worth tracking as official release notes and more comparisons emerge.

2026-09-09 ~ 2026-09-09 · 20 related posts

Full story(6 episodes)→

• Episode 1: GPT-Image-2.5 Reportedly Launches in ChatGPT, Unconfirmed by OpenAI(2026-09-07, 5 posts)
• Episode 2: OpenAI launches ChatGPT Images 2.5 with Flare and Sunburst API models(2026-09-09, 43 posts)
• Episode 3: ChatGPT quietly upgrades to GPT-Image-2.5 with new Sketch feature(2026-09-09, 20 posts)
• Episode 4: GPT-Image-2.5 Variants Sweep Major Image Arena Leaderboards(2026-09-09, 6 posts)
• Episode 5: OpenAI Ships GPT-Image-2.5 Flare and Sunburst via API(2026-09-09, 4 posts)
• Episode 6: GPT Image 2.5 Impresses Users With Character Consistency(2026-09-09, 3 posts)

• [source] OpenAI adds Sketch to ChatGPT: draw your idea and let AI render it — OpenAI · 2026-09-09
• [source] GPT-Image-2.5 appears in ChatGPT; classic noise artifact test shows mixed results — mark_k · 2026-09-09
• New Sketch feature in GPT Image 2.5 praised for outsized productivity gains — lukaszkaiser · 2026-09-09
• First samples shared from ChatGPT Images 2.5, OpenAI's newly released image model — DeryaTR_ · 2026-09-09
• mark_k on GPT-Image-2.5 noise artifacts: not worse, but not much better either — mark_k · 2026-09-09
• ChatGPT Images 2.5 Rolls Out, Users Report Impressive Results — xiaohu · 2026-09-09
• Hands-on: ChatGPT Images 2.5 shows precise local editing of infographics — xiaohu · 2026-09-09
• Blogger shares fine-editing comparison shots of ChatGPT Images 2.5 — xiaohu · 2026-09-09
• Infographic editing demo shows precise local edits and layout adjustment — xiaohu · 2026-09-09
• Testing ChatGPT's Image Gen 2.5: a subtle half-step upgrade — Aizkmusic · 2026-09-09
• [source] Hands-on with ChatGPT Sketch and Images 2.5: rough doodles become posters — APPSO · 2026-09-09
• ChatGPT Images 2.5 is out: sketch-to-image, targeted edits, readable text — aitrendz_xyz · 2026-09-09
• GPT-image-2.5 nails the slumped-against-wall pose other models get wrong — aitrendz_xyz · 2026-09-09
• Prompt turns a single character image into a pixel-art idle animation — aitrendz_xyz · 2026-09-09
• GPT-Image 2.5 fakes a full product photoshoot, down to the barcode — aitrendz_xyz · 2026-09-09
• ChatGPT Images 2.5 generates event summary slides with clean text — aitrendz_xyz · 2026-09-09
• Prompt turns any character into a 4×4 pixel-art combat sprite sheet — aitrendz_xyz · 2026-09-09
• GPT Image 2.5 sketch mode turns rough scribbles into stunning artwork — aitrendz_xyz · 2026-09-09
• ChatGPT Images 2.5 generates website mockups with no broken text — aitrendz_xyz · 2026-09-09

1 near-duplicate retellings: ElonBaldMusk