OpenAI Drops ChatGPT Images 2.5 With Sketch, 50% Faster — SkimNews
Get the Tech newsletter
Daily tech — startups, AI labs, chips, the launches that shape the next decade. Free.
- OpenAI released ChatGPT Images 2.5 on September 8, 2026, touting sharper details, faster generation, more precise editing, and improved natural lighting and texture rendering over Images 2.0.
- Image generation latency dropped by up to 50% compared with Images 2.0, according to OpenAI, alongside better multi-turn editing instruction following and improved subject preservation from reference photos.
- OpenAI introduced a new Sketch feature that lets users draw directly inside ChatGPT as a reference for image generation, plus templates for popular image formats and a prompt-sharing mechanism.
- Two developer API tiers — GPT-Image-2.5 Flare (default, 50% lower latency than GPT-Image-2) and GPT-Image-2.5 Sunburst (for premium editing workflows like campaign and product imagery) — are available to build around in third-party apps.
- Images 2.5 rolled out immediately to ChatGPT, ChatGPT Work, and Codex users across all tiers on desktop, mobile, and web, arriving one week after the GPT-6 Astra launch.
Why it matters: OpenAI is shipping flagship creative tools at a weekly cadence: Images 2.5 drops seven days after GPT-6 Astra, giving ChatGPT's hundreds of millions of users and API developers simultaneous access to a 50% faster, sketch-aware image engine — tightening the competitive gap with Midjourney, Adobe Firefly, and Google's image products on speed and creative-control benchmarks.
Ask SkimNews
