xAI launches Grok Imagine 1.5 Preview

// 2h agoMODEL RELEASE

xAI launches Grok Imagine 1.5 Preview

xAI has released Grok Imagine 1.5 Preview, an image-to-video AI model that generates realistic video content from static images. Accessible via the xAI API and grok.com, the update introduces support for camera direction, pacing, and native audio synchronization.

// ANALYSIS

xAI is moving incredibly fast to build out its multimodal features, proving that Grok is transitioning from a chatbot to a comprehensive creative platform.

–Integrating audio synchronization directly into the image-to-video workflow is a huge win, tackling one of the most frustrating limitations of current AI video tools.
–Pushing the preview to the API first leverages the developer ecosystem to battle-test and refine the model under diverse real-world workloads.
–The focus on precise prompt-following and camera direction shows xAI is targeting professional creator workflows rather than just casual users.

// TAGS

grok-imagine-1-5-previewxaigrokimage-to-videovideo-genmodel-releaseai-video

DISCOVERED

2h ago

2026-06-05

PUBLISHED

2h ago

2026-06-05

RELEVANCE

8/ 10

AUTHOR

SpoonOS_ai

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

MODEL17m ago

Gemma 4 12B Assistant accelerates decoding

The Gemma 4 12B IT Assistant checkpoint has caused developer confusion, as it is actually a speculative decoding drafter model rather than a standalone chatbot. When configured in tools like vLLM alongside the primary model, it accelerates inference via Multi-Token Prediction without degrading quality.

BENCHMARK17m ago

Google's Gemma 4 12B model faces criticism for slow local performance and poor multimodal generation on Apple Silicon.

A developer tested Google's Gemma 4 12B model on a MacBook Pro M5 Max with 128GB of unified memory, finding its performance disappointing for a model of its size. Achieving only 44 tokens per second, the developer noted that the model's generation quality was subpar—specifically criticizing a produced lava lamp image—and recommended developers stick with Qwen 3.6 27B or 35B instead.

OPEN SOURCE43m ago

A Windows companion suite for the OpenClaw AI agent platform, featuring a system tray app, a WebSocket shared library, and a PowerToys Run/Command Palette extension.

openclaw-windows-node is a Windows companion suite designed for the self-hosted OpenClaw AI agent platform. It enables deeper integration on Windows systems via three main components: a WinUI 3-based system tray application to manage gateway connections and settings, a shared .NET library (OpenClaw.Shared) that communicates with the central OpenClaw gateway using WebSockets, and a PowerToys Command Palette extension that allows users to trigger agent actions directly from their Windows desktop command interface.

xAI launches Grok Imagine 1.5 Preview