A while back, I went on a trip to Germany and took a ton of photos. I thought about editing them into a travel video, but honestly, just using photos to make a video… it felt kind of boring. So I figured, why not try using Grok Build to auto-edit everything for me? Turns out, the final result was amazing. In this video, only a small segment was recorded by me. For the rest, I just provided photos, and Grok Build transformed them into a video, making the whole thing come alive while still keeping the authentic vibe of a travel diary. It even handled everything—organizing the photo materials, selecting the best shots, arranging the pacing, and adding the BGM—all automatically. All I said was: "Make a high-quality travel documentary from the materials in the folder. Keep it real, don’t overdo it." In less than 10 minutes, the video was done. I’m not exaggerating—Grok Build is seriously fun to use right now. Integrating raw image and video generation capabilities into the Agentic workflow, with super-fast response times, I’ve already upgraded to the 300U Heavy plan. Just the built-in video generation tools alone are worth it. By comparison, GPT currently only has image generation, and Claude doesn’t even have an official image generation feature yet. To move toward a more comprehensive AGI, I think both image and AI video generation are essential. @elonmusk really has vision—xAI was right to focus on developing image and AI video generation from the start. Grok Build is absolutely the king of multimodal Agentic right now.