ChatGPT Adds Virtual Try-On, Product Favorites

// 1h agoPRODUCT UPDATE

ChatGPT Adds Virtual Try-On, Product Favorites

ChatGPT now lets users virtually try on clothing and accessories using selfies or product images, then save products in Favorites. The experience is powered by ChatGPT Images 2.5, though OpenAI cautions that results do not guarantee fit or accurate appearance. [OpenAI Help Center](https://help.openai.com/en/articles/11128490-shopping-with-chatgpt-search)

// ANALYSIS

OpenAI is turning ChatGPT from a product-research assistant into a visual shopping surface, making image generation directly useful at the point of purchase.

–Virtual try-on reduces uncertainty around styling, but generated images remain previews rather than reliable sizing or fit simulations
–Persistent reference photos make repeat shopping faster while raising important questions about photo retention, privacy, and user control
–Favorites gives ChatGPT a lightweight shopping memory, keeping product discovery inside the assistant instead of sending users immediately to retailer sites
–The feature showcases Images 2.5’s stronger reference-image fidelity and editing consistency, capabilities OpenAI also highlights for developers [OpenAI](https://openai.com/index/introducing-chatgpt-images-2-5/)

// TAGS

chatgpt-shoppingmultimodalvisionimage-gensearchchatbot

DISCOVERED

1h ago

2026-10-02

PUBLISHED

1h ago

2026-10-02

RELEVANCE

6/ 10

AUTHOR

ShowsAli

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

MODEL17m ago

AWS Strands Decider 2B Opens Decision-Model Race

AWS released Strands Decider 2B, an open-source 1.9B-parameter model that selects among predefined options, scores inputs, and returns calibrated confidence without generating text. It runs locally in roughly 115ms on an RTX 3090 and includes its training data and scripts. [Announcement](https://strandsagents.com/blog/introducing-strands-decider/)

UPDATE51m ago

Synara Flags Unsent Drafts Across Threads

Synara now shows a pencil icon beside threads containing unsent prompts, helping users recover unfinished work after switching conversations. The small UX improvement strengthens its local-first workspace for managing multiple coding-agent sessions.

TUTORIAL2h ago

Anthropic’s Webapp-Testing Skill Gives Agents Browser QA

Anthropic’s open-source webapp-testing Agent Skill gives coding agents a repeatable Playwright workflow for testing local web apps, including server management, browser interactions, screenshots, and console inspection. The video demonstrates its value for responsive-layout and booking-flow validation.