OpenAI Launches ChatGPT Images 2.5: Up to 50% Faster Generation, Sketch Guidance, and Two New API Models
Dimillian · x · 2026-09-09
OpenAI officially rolled out ChatGPT Images 2.5 across all ChatGPT, ChatGPT Work, and Codex tiers on desktop, mobile, and web.
Key improvements:
- Up to 50% lower generation latency vs Images 2.0
- More natural lighting, textures, and recognizable subjects
- Better detail preservation across repeated edits
- Comment directly on images to target changes
- Better handling of complex layouts, styles, and transparent backgrounds
New tools:
- @ Sketch: draw in ChatGPT to guide your image
- Templates: start from posters, merch, and more
- Share prompts alongside images for remixing
Two new API models: GPT-Image-2.5 Flare (better quality, editing, speed) and GPT-Image-2.5 Sunburst (higher precision for detailed work, longer generation times).
More from Multimodal
- Dev uses AI to model vintage change machines in Blender for his game — AIandDesign · 2026-09-09
- geoface: a GeoGuessr-style game with diffusion-generated faces by region — hamostaf04 · 2026-09-09
- Colorizing Video With Wan 2.2 Fun Control, a Demo — GdaTyler · 2026-09-09
- Developer open-sources HTML/CSS video templates made purely with prompts — round · 2026-09-09
- Andrew Mayne uses GPT-Image 2.5 to turn a sketch into animated GIFs with a few notes — iamrobotbear · 2026-09-09
- TURNtable Viewer 1.4.3 turns 360° turntable image sets into pseudo-3D billboards in Blender — o0ANARKY0o · 2026-09-09