OpenAI has upgraded image generation: now you can even create GIFs
🎨 OpenAI has upgraded image generation: now you can even create GIFs The company introduced Images 2.6 with new capabilities for creating and editing visual content. Now AI can turn text and pictures into animations, edit individual frames and...
- 01.🎨 OpenAI has upgraded image generation: now you can even create GIFs The company introduced Images 2.6 with new capabilities for creating and editing visual content
- 02.Now AI can turn text and pictures into animations, edit individual frames and...
🎨 OpenAI прокачала генерацию изображений: теперь можно создавать даже GIF Компания представила Images 2.6 с новыми возможностями для создания и редактирования визуального контента. Теперь ИИ умеет превращать текст и картинки в анимации, редактировать отдельные кадры и регулировать скорость GIF. Улучшили и работу с референсами: персонажи, лица и предметы должны сохранять узнаваемость даже после серии изменений. Для разработчиков выпустили две модели: Flare генерирует изображения примерно за 6 секунд, а Sunburst делает упор на качество и детализацию. При этом популярность генерации продолжает расти: уже 4 миллиарда изображений в неделю против 3 миллиардов в сентябре. Обновление доступно в ChatGPT, Codex и API. Источник
Related Intelligence
All stories →OpenAI released a new cybersecurity model. Is that enough?
OpenAI's newest cybersecurity model comes out as AI labs face scrutiny of their work to protect digital infrastructure.
Google's Gemini Omni 1.2 Flash stretches AI video clips to 15 seconds and cuts pricing by 30 percent
Google Deepmind is making Gemini Omni 1.2 Flash generally available. The video-generation model now creates clips up to 15 seconds long, can be edited step by step via conversation, and costs just $0.07 per second at 720p, 30 percent less than its predecessor. Users who draft in…
Anthropic has reduced the cost of updating AI agent statuses in Claude Code by 99%
💸 Anthropic has reduced the cost of updating the statuses of AI agents in Claude Code by 99% Previously, Claude Code re-read all correspondence of the background agent every 30 seconds to briefly inform the user what he is doing. Moreover, for this purpose the same model was used as that of the agent himself.…