Google's Multimodal Canvas is a testbed for multimodal prompts
Google Deepmind has launched Multimodal Canvas, an experimental testing console for developers. With a valid API key, they can use Gemini 1.5 Flash to quickly test multimodal prompts with text, drawings, camera shots, and other images. Gemini 1.5 Flash is faster and less expensive than the larger Gemini 1.5 Pro, and supports a 1 million token context window.
Let's play pictionary with Gemini ✏️ on Multimodal Canvas: an experiment powered by 1.5 Flash.
Developers can try it out with a Gemini API key → https://t.co/m0DqfO0Trf pic.twitter.com/mRsRuiK6Sd
- Google DeepMind (@GoogleDeepMind) July 3, 2024
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
Subscribe nowRead on for the full picture.
Subscribe for hype-free coverage.
- Full access to every article on THE DECODER
- No ads
- Join the comments and community discussions
- A weekly AI news recap via mail
- 6x/year: "AI Radar" — deep dives on the AI topics that matter most
- Daily AI news, always up to date
- Our full ten-year archive
- Covered by a team with 10+ years in AI