Dejia Xu

✨ Research Lead @LumaLabsAI. @WNCG_UT @VITAGroupUT

[Dejia Xu @Ir1dXD]

@theopanag7 Hope you enjoy your well-deserved rest 🥹 Best of luck on the next chapter!!

[Luma @LumaLabsAI]

Direction goes in. Cinema comes out.

Ray3.2 is here → https://t.co/TuAuFhZDBn

[Dejia Xu @Ir1dXD]

@TianweiY @reve @arena Very impressive! Congrats!!

[Dejia Xu @Ir1dXD]

@_sam_sinha_ @BerntBornich @1x_tech Congrats!!

[Dejia Xu @Ir1dXD]

@baaadas @LumaLabsAI It’s been a privilege working with you, and I can't thank you enough for being more than just a boss, but a true mentor. Wishing you the absolute best in your next chapter!

[Luma @LumaLabsAI]

The Uni-1.1 API is live today. Built-in prompt enhancement, research, and reference gathering at the API level.

Trained in collaboration with Hollywood cinematographers, VFX artists, and world-class artists across cultural forms.

Less than half the price and latency of comparable models.

Designed for builders shipping in production — and ranked top 3 lab in the Image Arena across Text-to-Image and Image Edit.

Start Building → https://t.co/bvlLzjK9QQ

[Arena.ai @arena]

Exciting news: UNI-1.1-Max and UNI-1.1 debuts making @LumaLabsAI the #3 lab in the Image Arena across both Text-to-Image and Image Edit! These are versions released without agentic search.

Text-to-Image Arena
- UNI-1.1-Max #6 overall (1193), +12 points over MAI-Image-2
- UNI-1.1 #7 overall (1190), +13 points over Reve-v1.5

Multi-Image Edit Arena
- UNI-1.1-Max #7 overall (1315), +21 points over Seedream 4.5
- UNI-1.1 #8 overall, (1298)

Single-Image Edit Arena
- UNI-1.1-Max #7 overall (1337)
- UNI-1.1 #11 overall, (1310) on par with Grok-Imagine-Image (20260207)

Congratulations to @LumaLabsAI on this solid performance!

[Dejia Xu @Ir1dXD]

@ayaanzhaque Congrats!!

[William Shen @shenbokui]

New viz mode drops.
Genuinely the coolest visualization I have seen.
We visualize UNI-1's latent embedding space as a 4D hypersphere using SO(4) rotation.
You can see how nearest neighbors move together (second half of the video).
Implemented by @sane_codes
Embedding is using siglip2 by @mtschannen @XiaohuaZhai @giffmana

[William Shen @shenbokui]

Most image models are good at one thing.
Uni-1 has been good at everything we've thrown at it.

Our team generated thousands of images leading up to Uni-1 launch. We embedded them all into a single map where visual similarity determines proximity. The result speaks for itself.

[Baifeng @baifeng_shi]

Humans can see in high-res, high-FPS in real-time. Why can't VLMs?

Introducing AutoGaze: ViTs/VLMs "gaze" only at key video regions! Up to 4-100x token savings, 19x speedup, and enables scaling to 4K-res 1K-frame videos.

📄 https://t.co/GhbWZwMAg7
🌐 https://t.co/mEJ991MAIR
🤗 https://t.co/FOfc2QRThi

(1/n)🧵

[Luma @LumaLabsAI]

We are loving the energy around Uni-1!

Quick note since we’re seeing questions:

With Luma Agents, requests can route across models. If you want to make sure you’re using Uni-1, here’s how:

- Select Create Image → Uni-1
- Or, explicitly ask the agent to use Uni-1
- Check the model label on outputs to confirm

API access coming soon for more direct testing.

Keep the feedback coming, and keep on creating → https://t.co/zjJZMt8Dt6.

[Yiqing Liang @YiqingLiang2]

🙏 Grateful and Proud beyond words to be part of the incredible team that built UNI-1 @LumaLabsAI!

Intelligent, directable, cultured — and the manga generation? See these 👇 and try it FREE today here: https://t.co/UXnTp8YCYi!

Plus we are hiring!

[Jiaming Song @baaadas]

A fixed text token length is a limitation of most existing text-to-image models. In Uni-1, we engineered around this, so that it can take at least 3500 tokens (even in markdown) if you want to promptmaxx. The differences is huge between Uni-1 (1st image) and Flux 2 (2nd image).

[Jiaming Song @baaadas]

Thanks for the amazing team that made this possible!

We saw a significant improvement on the model even in the 2 weeks between the announcement and the launch.

Now, to new heights!

[Theo Panagiotopoulos @theopanag7]

Unified models in a unified workspace 🪄

One step closer. Incredibly proud of the Luma team!

[Luma @LumaLabsAI]

Uni-1 is here! A new kind of model that thinks and generates pixels simultaneously. Less artificial. More intelligent.

[William Shen @shenbokui]

UNI-1 is intelligent, directable, cultured. Incredible range it can do.

Incredibly proud of the world-class team building a world-class model.
It’s a daunting task to go up against industry giants like Deepmind/OpenAI/Bytedance.

More to come! API, technical report, model card…

Come join us!

[William Shen @shenbokui]

Excited to introduce Uni-1, our new multimodal model that *unifies* understanding and generation.

TLDR: a team of ~15 researchers is going pound-for-pound with nano banana and gpt image 🧵

[Luma @LumaLabsAI]

Introducing Luma Agents. Creative agents that make you prolific. You set the direction. They build with you, seeing what you see and helping teams explore further, iterate faster, and watch ideas multiply.