{"id":"92aa5c6d-d488-4d90-bca0-75a4e7ce1672","url":"https://api.tumn.com/news/92aa5c6d-d488-4d90-bca0-75a4e7ce1672","title":"Training Text-to-Image Models Without a VAE","summary":"Comments","sections":[],"faq":[],"sources":[{"url":"https://www.linum.ai/field-notes/pyramid-jit","title":"Hacker News 프런트페이지","publishedAt":"2026-10-06T20:24:52.000Z"}],"author":"TUMN 큐레이션","aiAssisted":false,"reviewStatus":"automated","reviewNote":"원문 제목과 공개된 발췌를 인용하고 원문으로 연결합니다. 내용을 재작성하거나 요약하지 않았습니다.","publishedAt":"2026-10-06T20:24:52.000Z","modifiedAt":"2026-10-09T22:24:39.000Z","checkedAt":"2026-10-09T22:24:39.242Z","language":"ko","kind":"link","sourceLabel":"개발","profile":null,"via":null,"formats":{"json":"https://api.tumn.com/news/92aa5c6d-d488-4d90-bca0-75a4e7ce1672.json","markdown":"https://api.tumn.com/news/92aa5c6d-d488-4d90-bca0-75a4e7ce1672.md"}}