This sounds so fun. I wonder if you take that description and feed it to a text2... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

3abiton 19 days ago | parent | context | favorite | on: Trying out QvQ – Qwen's new visual reasoning model

This sounds so fun. I wonder if you take that description and feed it to a text2img model like flux, what would be the results.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact