OpenAI · Status at source date: Newsletter archive
OpenAI releases ChatGPT Images 2.0 with sharper editing and multilingual rendering
OpenAI has released ChatGPT Images 2.0, a new image model positioned as a step change in instruction following, object placement and relationships, and dense text rendering across aspect ratios. The model handles complex visual tasks with less prompting required, drawing on expanded visual and world knowledge to fill in missing details.
What changed
Multilingual accuracy has been improved.
Images 2.0 is available to all ChatGPT and Codex users. Images with thinking: extended reasoning during generation: are reserved for Plus, Pro, and Business tiers. The underlying model, gpt-image-2, is available in the API.
Why it matters for advertisers
For you, this means a meaningful upgrade for marketing teams using AI image generation for ad creative, social posts, and concept design: particularly where multilingual creative localisation has previously required separate models or post-generation editing. Worth re-running the benchmark prompts your creative team uses to compare against current production tools.
Perspective from the original PMC newsletter.Sources & contributor credit
- Newsletter coverage · Paid Media Collective newsletter
Original newsletter text, contributor labels and media for this update.
- Source referenced in newsletterOpenAI
Linked from the original newsletter. The source publication date has not been independently confirmed.
Original creator unverified
The original creator has not yet been verified. Newsletter curation and publication do not establish original authorship.
Attribution evidence and limitations
Full attribution review pending.
A source link alone does not establish original authorship.
Original image and video creators have not yet been verified.
- Published on this site
This update reflects the dated source reporting. Availability may have changed. Further coverage of this same development will be added to this page.
Original newsletter text and archive evidence
OpenAI releases ChatGPT Images 2.0 with sharper editing and multilingual rendering
OpenAI has released ChatGPT Images 2.0, a new image model positioned as a step change in instruction following, object placement and relationships, and dense text rendering across aspect ratios. The model handles complex visual tasks with less prompting required, drawing on expanded visual and world knowledge to fill in missing details. Multilingual accuracy has been improved.
Images 2.0 is available to all ChatGPT and Codex users. Images with thinking: extended reasoning during generation: are reserved for Plus, Pro, and Business tiers. The underlying model, gpt-image-2, is available in the API.
For you, this means a meaningful upgrade for marketing teams using AI image generation for ad creative, social posts, and concept design: particularly where multilingual creative localisation has previously required separate models or post-generation editing. Worth re-running the benchmark prompts your creative team uses to compare against current production tools.
Source captured . No explicit first-contributor label was provided for this update.
