Igor Petrovski

Multimodal Research @ Meta Superintelligence Labs | ex - Google DeepMind, Google, ETH Zurich

[Igor Petrovski @ipetr0vski]

Muse Image & Video (preview) is here! 🧵

Two things I'd like to highlight:
* Agentic image generation: through scaling test time compute & usage of tools we're able to significantly improve model's performance.
* A shared pretraining backbone that enables high fidelity image & video generation.

Check out the blogpost for more details:
https://t.co/NMkq2PMUjL

[Igor Petrovski @ipetr0vski]

@VictoriaLinML Congrats Victoria!!

[Igor Petrovski @ipetr0vski]

@RafaelValleArt @rimelabs @lilyclifford Congrats Rafa! Best of luck.

[Igor Petrovski @ipetr0vski]

@RylanSchaeffer @Meta Best of luck, Rylan!

[Jiahui Yu @jhyuxm]

Muse Spark 1.1 is here! Available today via API and on https://t.co/VbuADfMjSt.

Of all the agentic use cases, I’m most excited about this one: going from a single video shot straight to task completion. 🚀

We’ve also polished and launched Computer Use and Video-Audio Perception for Muse Spark 1.1. Read more: https://t.co/6ITTaeM0Pp

[Alexandr Wang @alexandr_wang]

1/ muse spark 1.1 is an industry-competitive agentic and coding model. across many agentic evals it rivals gpt-5.5 and opus-4.8.

available now through the new meta model api and in meta ai. 🧵

[Ethan Weber @ethanjohnweber]

Today we launched Muse Image and are previewing Muse Video! 🚀

https://t.co/sVPBIHGgzv 👈

Muse Image does agentic image generation! It's great at tool use and search. I highly recommend trying it out on https://t.co/JBfhbJUJLB!

Excited to continue! 🧑‍🍳🔥

[Yilun Xu @xuyilun2]

1/ It's been so much fun building Muse Image/Video from scratch with the team. The story of Muse Image's agentic behavior did not begin as a designed feature. It began as an surprise to us, from the self-refinement behavior to the test-time scaling!

https://t.co/cK8Yn4XE47

[Hui Ding @huiding111]

Muse Image and Muse Video are officially out! 🎉 Honestly so proud of this team. So much heart went into this, and it's been a blast building it with such talented folks. Go check out what we made — and give Muse Image a spin on Meta AI 👇

Blog: https://t.co/S1Ih7WJhKz
Try it on Meta AI: https://t.co/NFPYREAYgG

[Filip Radenovic @filipradenovic]

My favorite are video generated examples where we preview our video capabilities, see examples in our blog post: https://t.co/CD4HIYRfaZ

[Yushi Hu @huyushi98]

We built the entire Muse-Image/Video post-training stack in just a few months, and we are amazed everyday by how well everything scales for multimodal generation, beyond language. 😎

Super grateful to work in such a talent-dense team!

https://t.co/FTUlYQgKup

[Igor Petrovski @ipetr0vski]

The reference-to-image capability is quite strong. a few examples

[Jiahui Yu @jhyuxm]

Today we're launching Muse Image and previewing Muse Video, our next Multimodal models after Muse Spark!

Generation goes Agentic and it's way more fun and powerful: it searches, codes, self-reflects, and calls tools to get things right. It's also freeform, interleaving text and images with multi-reference support.

Try Muse Image now at https://t.co/VbuADfMRI1!

[Tim Brooks @_tim_brooks]

We’re launching Muse Image today!! 🎉 It’s an agentic image gen model that plans, writes code and uses search tools, and refines its own outputs in chain-of-thought. Image performance improves as we scale test-time compute with higher reasoning. https://t.co/LUuvpixsui

[Igor Petrovski @ipetr0vski]

works well with exploring different hairstyles too!

[Alexandr Wang @alexandr_wang]

1/ releasing muse image today — the first image generation model from MSL. it's agentic: pairs with muse spark to reason through your prompt, search the web, and plan before it generates. people get what they meant on the first try. live now in the Meta AI app.

[Arena.ai @arena]

Exciting news: Meta’s Muse Image just claimed #2 in the Image Arena!

Muse Image from @AIatMeta now ranks second only to OpenAI's GPT Image 2, outperforming Nano Banana, Grok Imagine, MAI Image, and many other leading image models.

It holds #2 across the board: Text-to-Image, Single-Image Edit, and Multi-Image Edit. Congrats to the Meta team on this incredible milestone!

[Igor Petrovski @ipetr0vski]

Finally, today marks exactly one year since I joined the Meta Superintelligence Labs and I couldn't be more proud & honored to be a part of such an incredible team.

[Igor Petrovski @ipetr0vski]

Muse Image & Video (preview) is here! 🧵

Two things I'd like to highlight:
* Agentic image generation: through scaling test time compute & usage of tools we're able to significantly improve model's performance.
* A shared pretraining backbone that enables high fidelity image & video generation.

Check out the blogpost for more details:
https://t.co/NMkq2PMUjL

[Igor Petrovski @ipetr0vski]

Also, the product integration in the Meta AI app (https://t.co/vMCnEIPyyf) is pretty cool! You can generate highly personalized images and explore cool presets.

[Igor Petrovski @ipetr0vski]

@_rohitgirdhar_ @sainingxie It was a pleasure working with you, best of luck!

[Igor Petrovski @ipetr0vski]

@mervenoyann @andimarafioti @micuelll @orr_zohar congrats!