Higgsfield AI has integrated Google's multimodal video model Gemini Omni Flash into its platform and made it callable directly from Anthropic's Claude through the Model Context Protocol (MCP), letting users generate and edit images and video without leaving the chat. The workflow is presented as chat-native, with demos showcasing "realistic AI VFX" in which text holds steady across frames.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.