PeizeSun

@xAI AGI | @grok Multimodal, Imagine | prev Meta HKU XJTU

[PeizeSun @PeizeSun]

Grok Imagine is not only a family of models, it is an ecosystem for entertainment and intelligence.

👇👇👇Generated by the latest Grok Imagine image and video model

[Grok @grok]

Grok @Imagine 1.5 Preview is here

Try it today in the API: https://t.co/x4Yt13xRu7

[PeizeSun @PeizeSun]

Let’s go, Imagine !

[Arena.ai @arena]

Grok-Imagine-Video-1.5-Preview (720p) has landed #1 in the Image-to-Video Arena!

This is a massive +52 pt improvement over Grok-Imagine-Video (720p), surpassing the best video models Seedance-2.0 and HappyHorse.

Congrats to @xAI and @elonmusk on this big achievement!

[PeizeSun @PeizeSun]

Grok Imagine as foundation of game generation

[Grok @grok]

Prototyping game assets directly with Grok @imagine

[PeizeSun @PeizeSun]

Back to basics in audio generation

[Feiyan zhou @Feiyanzhoubpp]

🚀 Does high-quality audio generation really require latent compression?

Excited to share our new paper🚀🚀🚀
WavFlow: Audio Generation in Waveform Space.

WavFlow removes the audio tokenizer / VAE bottleneck and performs flow matching directly in raw waveform space.

Instead of generating compressed latent tokens, WavFlow directly models waveform patches end-to-end, achieving competitive or better performance than latent-based methods on both Video-to-Audio and Text-to-Audio benchmarks.

Key ideas:
• waveform patchify
• x-prediction flow matching
• amplitude lifting for stable raw-space training
• large-scale 5M video-text-audio training pipeline

Paper: https://t.co/bvWuPxdH9c
Demo: https://t.co/i5uDLisXpx
Code: https://t.co/xsGxtx8xR3
#AI #AudioGeneration #DiffusionModels #FlowMatching #MetaAI
Pop your headphones on 🎧 , turn on the sound📣, and listen to what our model can do!

[PeizeSun @PeizeSun]

@CMS_Flash @xai Legends never die, bro 🫡

[PeizeSun @PeizeSun]

@archanfel_anoth 🐐🐐🐐🫡

[PeizeSun @PeizeSun]

Grok Imagine is becoming more and more intelligent

[X Freeze @XFreeze]

Grok Imagine Agent Mode (Beta) just released on grok web

This is not just basic image generation... it’s a full creative agent on an infinite open canvas

Tell it:
- “Generate a 1-minute cinematic film”
- “Create a complete manga set”
- “Build UGC product stories”

…and it plans, generates, edits, and iterates everything in one workspace

You don't need to tab-switching...or starting over
It's just pure agentic flow

This is the biggest leap yet for Grok Imagine

[PeizeSun @PeizeSun]

@JackCaiXun To our goat 🐐— sent from anonymous warroom

[Yukun @YknZhu]

For everyone who wanted better lip sync and audio, we heard you loud and clear!

Super proud of the team for dropping this Grok Imagine update 🔥

[PeizeSun @PeizeSun]

You will be amazed by Quality mode !

[xAI @xai]

Introducing Quality mode on Grok Imagine – powered by our most advanced image generation model.

Quality mode gives you enhanced details, stronger text rendering, and higher levels of creative control.

Now available on web and mobile.
Try it at https://t.co/zGhs9czkC5

[PeizeSun @PeizeSun]

This is V1.0

[Arena.ai @arena]

Today we’re launching the Video Edit Arena to evaluate the frontier capability of video models!

- #1 Grok-Imagine-Video, @xAI
- #2 Kling-o3-pro, @Kling_ai
- #3 Kling-o1-pro, @Kling_ai
- #4 Gen4-aleph, @Runwayml

The leaderboard is powered by thousands of real-world community votes. Click the Edit button in Video Arena to edit any video and compare top model outputs.

More models coming soon!

[PeizeSun @PeizeSun]

Imagine team at @xai is the best media generation team !

[Yukun @YknZhu]

At @xai we are making media creation more accessible, enjoyable and useful. Lots more creative features coming soon!

Thanks to the amazing team that worked around the clock to ship this, and our captains @Guodzh @imhaotian ❤️

[PeizeSun @PeizeSun]

@imhaotian @elonmusk Our Super Man 🫡

[PeizeSun @PeizeSun]

@Guodzh To our captain🫡

[PeizeSun @PeizeSun]

Try Reference to Video in Grok Imagine now !

[Xiang Li @XiangLi5217365]

We are supporting Reference to Video in Grok Imagine now!

You can create videos with up to 7 ingredients, try it!

[PeizeSun @PeizeSun]

Grok Imagine supports video extension now !

[Martin Ma @martin_ma_007]

Since @Grok Imagine v1.0 release, many of you requested video extension. We hear you!

It's available today 🎬

Enjoy, with more to come!!

[PeizeSun @PeizeSun]

Future is coming

[xAI @xai]

Since xAI was formed just 30 months ago, the small and talented team has made remarkable progress.

The future has never looked more exciting!

[PeizeSun @PeizeSun]

@hangg70 It is a great pleasure to work with you, Hang. Best wishes to your next journey~

[PeizeSun @PeizeSun]

faster, higher, stronger than 🍌🍌🍌

[Xuhui Jia @jia_xuhui]

Nano Banana has truly redefined what's possible with image generation models, pushing the boundaries of people's imagination when it debuted
Today, we're excited to introduce Grok-Imagine-Image: a new model that's both faster and better than Nano Banana.
Through this journey, we've built many of the essential building blocks needed to unlock the next generation of models and to keep fueling the growth and prosperity of the visual AI community.
Stay tuned... something incredible is coming very soon! But today, hello world, grok-imagine-image!

[PeizeSun @PeizeSun]

State-of-the-art video generation across quality, cost, and latency

[xAI @xai]

Understanding requires imagining. Grok Imagine lets you bring what’s in your brain to life, and now it’s available via the world’s fastest, and most powerful video API: https://t.co/tqQwQVgCEI

Try it out and let your Imagination run wild.