OpenAI releases ChatGPT Images 2.5 with sketch, point, and template tools
OpenAI has rolled out ChatGPT Images 2.5, a new image‑generation update that lets users sketch ideas, point to parts of an image, edit photos, use templates, and share prompts. The update focuses on better image quality, more precise editing, and faster generation, with OpenAI claiming up to a 50 % reduction in latency compared to Images 2.0.
What you can do with it
AI at Work →Create blog headers with Canva
What you get You can design social posts and make presentation slides.
Creates visual assets for content using templates and AI-generated design concepts.
- Who for
- marketers and founders
- Cost
- free tier
- Effort
- minutes
Use it for
- Create blog headers
- Design social posts
- Make presentation slides
How to set it up · From the article
- Consult ChatGPT for design ideas and aesthetic preferences.
- Open Canva and select a template that matches the AI suggestions.
- Adjust text, colors, and fonts to finalize the image.
Watch out Requires manual adjustment of templates to match AI suggestions
Canva in the tool directory · 3 changes covered
Key points from the news
- ChatGPT Images 2.5 adds sketch, point, and template editing tools.
- OpenAI claims up to 50% faster image generation compared to Images 2.0.
- More than 3 billion images are generated weekly by ChatGPT Images and GPT-Image models.
The new tools allow a rough doodle to guide the layout, a targeted comment to change a single detail, and a reference photo to preserve key characteristics. Users can also choose from ready‑made templates and share the prompt that produced an image, encouraging remixing and collaboration.
OpenAI reports that ChatGPT Images and its GPT‑Image models together generate more than 3 billion images each week, underscoring the scale of AI image creation today.
The story so far
2 episodes →- OpenAI releases ChatGPT Images 2.5 with sketch, point, and template toolsthis story
Want trending AI images? How to create cinematic, vintage and dreamy looks with ChatGPT 2.5
english.mathrubhumi.com · 24 September 2026
Loading the full article…
This text was published by english.mathrubhumi.com and written by Warda Zain. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
4sources- An AI beginner tries making note images with Canva and ChatGPTPress · note.com ·
- ChatGPT for Beginners: A Zero-Based Explanation for Executives on 'What Can It Actually Do?'Press · note.com ·
- ChatGPT's new image generation 'Images 2.5' makes creating images easier! 3 steps for beginnersPress · note.com ·
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Generative AI & Models
All →- Apiiro finds 1,122 public GitHub files with secrets saved by Claude Code · 1 src
- Thinking Machines releases Inkling 2 Small, a 594B MoE model with 17B active parameters · 8 src
- OpenAI releases GPT-6 Cyber, a Critical-rated model that outperforms predecessors in vulnerability detection and alignment · 25 src
- Google releases Gemini Omni 1.2 Flash with 15-second video generation and 30% price cut to $0.07 per second · 10 src
- US accuses Chinese executive of allegedly sharing Nvidia chip info with Beijing · 11 src
Comments
via GitHub Discussions