xAI just rolled out 10-second video generation in Grok... Imagine With big improvements across the board Much better video quality Clean, clear audio The timer option isn’t available yet and it’s pretty random rn Full rollout expected soon Grok Imagine is getting seriously good, fastshow more

GROK TEXT-TO-VIDEO – WORDS IN, CINEMATIC MAGIC OUT Grok... Imagine upgrades are magical! No base image. No warm ups. Just pure text straight into video. Quick Hit: •⁠ ⁠Type a prompt, Grok spits out video like it’s directing a trailer •⁠ ⁠Explosion → rocket launch? Cosmic portal? It handles the wild stuff •⁠ ⁠10-second clips will roll out like magic soon •⁠ ⁠Rivals like Runway, Pika, and Sora are holding on to their hats xAI went from chatbot to images to full video in under a year. Imagine the progress in year two. Actually, don’t - Grok will generate it! Source: Elon Musk, xAIshow more

Grok 4.5 is already the ridiculously fast, competent workhorse.... Somehow, xAI still has a much heavier version in mind. Call it “Grok Maximus”, the token-hungry monster you bring out for the 1% of problems where efficiency can go take the day off. It’s coming. xAI Grok / Writer: Annette, Grok Imagine Designer: Jannéshow more

Grok 4.7 is just around the corner. And it’s... bringing a much bigger brain. The new model is coming with 2.1 trillion parameters, up 40% from Grok 4.6. It’s also trained on SpaceX engineering data and built to power persistent Grok Bot teams that keep working in the cloud after you log off. Bigger model. Better engineering context. Agents that don’t clock out. Grok 4.7 is coming in hot. Grok SpaceXAI SpaceX / Writer: Annette, Grok Imagine Designer: Jannéshow more

Tried the new Grok Imagine on desktop and I'm... pretty impressed. Turns out there's an entire editing suite that makes it easy to change the subject / environment / style in any image. And it's seamless to animate the output with a video model that is much improved w/ Grok 0.9.show more

OMG the new Grok Imagine web update is EVERYTHING... 😍✨ The UI changes look absolutely AMAZING super clean, modern, and buttery smooth! Everything just flows better now, making image & video creation feel next-level intuitive and fun 🔥 xAI absolutely cooked with this redesign. The web experience hits different! Go check it out yourself 👉 Who else is obsessed with the new look?? 👀show more

AI in 2026 is no longer about who answers... better. It’s about who learns from the real world faster. OpenAI is elite in polish and broad capability. Anthropic is elite in reliability and execution quality. Google is elite in ecosystem and multimodal scale. Grok’s edge is different: real-time world signal + massive compute + extreme shipping velocity. Dates that matter: Nov 17, 2025: Grok 4.1 rolled out broadly. Jan 6, 2026: xAI raised $20B Series E, with Grok 5 already in training. Jan 28, 2026: Grok Imagine API launched. Feb 2, 2026: SpaceX announced acquisition of xAI. This is no longer “just another model launch cycle.” This is vertical AI infrastructure compounding in real time.show more

Seedance 2.0 got its perfect match on Higgsfield. Grok... Imagine and Seedance 2.0 - xAI's image model paired with the category-leading video model, natively inside the platform. Grok Imagine generates your reference image in 9+ styles, fast. Seedance 2.0 - ranked #1 in image-to-video - takes it further than any other model can. The best results out of Seedance 2.0 start here.show more

xAI is rolling out support for shareable Imagine templates... on the Grok web. Users can now create custom templates with 3 different options - Photo > Video - Photo > Style Edit - Photo > Edit > Video Additionally, the "Image Reference" template type is also in the works.show more

Big news for 𝕏 creators This weekend, 𝕏 is... awarding $1M, $500K, and $250K to the top three videos about Grok, made using Grok Imagine 1.0 The challenge: "Create an ad that shows off what makes Grok powerful, hilarious, truthful, or game-changing Rules: • Video must be made with Grok Imagine 1.0 • 30 seconds or less • Submit by quoting the original post in the Creators thread • Winners judged primarily on Verified Home Timeline impressions • US users only If you’ve been waiting for a reason to cook with AI video - this is it Have fun creating with Grok Imagineshow more

The Grok Imagine updates keep accelerating. Reference-to-Video + Video... Extend just landed! Live in ComfyUI on Day 0. The generation speed alone makes it worth trying. Reference-to-Video: add up to 7 reference images to generate consistent characters and scenes Video Extend: seamlessly extend any video with smooth, natural motion Workflows and more details about the Grok updates below ⬇️show more

A dog on a phone saying, “Yes, this is... dog.” That was it. And somehow, it broke the internet in 2011. Today, with Grok Imagine, you can take one stupid little idea and turn it into a polished video, a game, a song, or a whole series in the same day. Same weird ideas, far more ways to run with them. Grok xAI Nikita Bier / Writer: Annette, Grok Imagine Designer: Jannéshow more

xAI isn't playing around. They just released the Grok... Imagine API, a unified video + image generation toolkit, and it's already sitting at #1 on the Artificial Analysis Video Arena for both Text-to-Video AND Image-to-Video. It's beating: ● Google's Veo 3.1 & Veo 3 ● OpenAI's Sora 2 ● Runway Gen-4.5 ● Kling 2.5 Turbo The Numbers Don't Lie: ● 64.1% win rate against Runway Aleph in blind human evaluations ● 57% win rate against Kling o1 ● Best-in-class latency. Sub-20 second generation for 720p, 8-second videos. (up to 15-second video) ● Native audio generation baked right into video output (dialogue, music, sound effects, all synced) What Makes It Different It's built for real creative workflows: ✅ Text-to-video AND image-to-video in one API ✅ Video editing with prompt-based controls (add/remove objects, restyle scenes) ✅ Camera controls: zoom, pan, timelapse, pull-back ✅ Style transfers: cyberpunk, watercolor, anime, you name it ✅ Performance animation: map your movements onto characters ✅ Native audio-video sync (no post-production needed) Why the focus on speed and cost? The partner feedback that shaped this: "Quality alone isn't enough if latency and cost make iteration painful." So xAI optimized for all three. Speed. Cost. Quality. Already Integrated With: ● fal. ai ● ComfyUI ● InVideo ● Flora ● HeyGen xAI went from underdog to chart-topper. The Grok Imagine API is fast, affordable, and genuinely production-ready. If you're building anything with AI video, this just became the one to beat.show more

GROK 1.5 BEATS SEEDANCE 2.0? Let's do our own... test shall we? Image to Video 720p I will say this is an incredibly difficult prompt so good job xAI on the improvements you have made definitely a noticeable improvement over 1.0. Look forward to seeing 2.0! Prompt in below thread Seedance 2.0 - Imagine 1.5 xAIshow more

Keeping up with Grok Build is becoming a part-time... job. You can literally watch it getting better in real time. Less lazy. More autonomous. More accurate. Meanwhile, the team keeps shipping fixes, upgrades, tools, quality-of-life improvements, and new capabilities at a pace that's difficult to keep track of. Grok Build keeps moving the goalposts on what it could do yesterday. Grok xAI / Writer: Annette, Designer: Jannéshow more

Grok is about to get a lot more passports.... Tesla is bringing its in-car xAI assistant to India, Thailand, Singapore, the Philippines, and Malaysia. Which makes sense, because a car assistant gets much more useful when it can handle real-world chaos in real languages. Routes. Questions. Local navigation. Random curiosity from the passenger seat. Possibly one “unhinged” personality too many. The car used to answer with warning lights and a navigation screen. Now it is getting a personality that does more than beep politely. It actually talks back with a bit more brain behind it. Tesla Grok xAI / Writer: Annette, Grok Imagine Designer: Jannéshow more

AI video is getting cheaper without sacrificing quality. Great... to see TopviewAI become one of the first platforms to bring Hailuo AI (MiniMax)’s MiniMax H3 to creators. Native 2K output, 15-second clips, multimodal generation across text, image, audio, and video, plus it’s priced at just 30% of Seedance 2.0. That kind of price-to-performance ratio makes high-quality AI video much more accessible for creators and teams.show more