
Building @PhotaLabs | ex Research Scientist @Adobe. CS PhD from NYU | Generative Models
New York
Joined January 2017
- Tweets78
- Following171
- Followers1.1K
- Likes340
Pinned Tweet
Photography is deeply personal. It’s about people, relationships, and moments that matter — shaping how we remember the world and the people around us.
So excited to finally share what we’ve been working on - a personalized photo generation and editing model designed for your own photography. The idea is simple: your photos should still feel like you - preserving your identity, your expression, your story, while giving you the freedom to shape the image around it, or reimagine it.
What excites me most isn’t just the ability to generate something entirely new, but the chance to fix the small, real things — the missed moment, the person who wasn’t there, the expression that didn’t quite land — and finally arrive at the photo you had in your head all along.
Phota app is finally here!
We turn any photos into shareable moments. My favorites are turning analog into digital, and restyle my little monster 🐱.
Hope you live every moments, take photos, and let phota help you to make them fun!
Download at phota.app!
Come to say hi and grab a Polaroid snapshot! 📷
We is heading to #AdobeMAX!
Come chat AI, photography, and telling stories with your own photos. Meet Phota’s new iOS app and photo agent, get your Polaroid taken, or grab these cute stickers and magnets!
Find us at booth 327C in the Creative Park at Adobe MAX 2026. See you by the beach 🏖️!
1
5
499
Mengwei Ren retweeted
We also released a comprehensive benchmark for persistent identity across generation, editing, restoration, and multi-person scenes.
Compared with 1) model-specific identity (through per-person LoRA) and 2) In-context identity (from reference images):
IDEOGRAM4-LoRA, FLUX2-LoRA, FIRERED-LoRA
NB2, GPT-IMAGE-2, REVE-2.1, SEEDREAM-5-PRO
Read the full benchmark here: photalabs.com/blog/identity-…
Mengwei Ren retweeted
Introducing Phota Identity V2, the fastest, most accurate model for persistent identity.
Train once with 5 photos in 1 minute, then use that identity across supported models, including NB and GPT Image.
The hardest part of generative visual AI isn't creating one great image. It's creating the same person or character again and again.
Built for premium content, digital twins, and brand storytelling at scale.
Create with more expressive faces, natural skin, and the freedom to put anyone in any scene.
Mengwei Ren retweeted
ChatGPT Images 2.5 is already great. Phota Identity makes it even better.
The model that knows your subject best, paired with the model that knows the world best.
You can now bring your Phota subjects and characters to Flare and Sunburst. Take your brand character anywhere.
One of the most interesting subtleties of preserving identity: the bar gets much higher when you’re looking at generated photos of yourself or someone you know well. Interested? Find out more in our identity benchmark!
When inspirations are hard to describe in text, a visual reference makes it much easier. My all time favorite feature StyleMe (in Phota Studio) is now available through Phota API 🥳
/remix is now public on the Phota API 🎉. The most-loved feature in Phota Studio (aka Style Me).
Remix people and pets into new styles, scenes, and moments, while keeping their identity intact.
You control what the style reference changes and what stays true to the original image.
A few interesting use cases below ↓
4
727
Mengwei Ren retweeted
We've gotten questions about how Phota works, so we wanted to share more about what we've built.
Phota, like many modern AI products, is a system of multiple models, each optimized for a different part of the generation pipeline.
Our proprietary model focuses on identity, which enables us to generate and edit photos of real people and pets.
For base image generation, Phota uses leading foundation models (both open and closed source - including Nano Banana). On top of those, we've trained our own identity model on both in-house data and user-uploaded photos to preserve identity consistently. That identity layer is the core of Phota's differentiation.
Phota has always been built as a multi-model system; we have not presented it as a single foundation model trained end-to-end from scratch. From the beginning, our core research effort has been focused on identity and photography.
Phota was built by former Adobe researchers who have spent years working on image models. Our launch this week focused on the product experience and the outputs - but we've also heard the interest in going deeper on the underlying research, and we're excited to share more over time.
We invite you to try Phota yourself, and we're eager to hear your feedback.
Try Phota Studio today at: studio.photalabs.com
Read more in the blog post here: news.photalabs.com/blog/the-…
2
361
Fix the little imperfections, tweak the composition, bring people into your frame, or reimagine the moment entirely — all while still feeling like you. Try Phota Studio today at studio.photalabs.com 📷
Today, we introduce Phota Studio and Phota API, powered by our photography model that brings flagship image model capabilities, personalized to you.
With personalization, an image model stops being just playful and starts becoming useful for photography.
With Phota Studio, you can:
- Reimagine composition, lighting, or posture while still looking like yourself
- Create editorial, stylized, and studio-quality portraits of yourself, or bring someone you love into the frame
- Revive the blurred shot, bring in the person who missed the group photo, fix the awkward expression - all without losing what made the moment worth keeping
With Phota API, you can finally build photo experiences where real people are the core. Marketing assets, editorial shoots, wedding photography: workflows that needed identity fidelity that GenAI couldn't deliver. Until now.
Ultimately, we want to make compelling photographs accessible to everyone. Phota API and Phota Studio start to make that possible: empowering people to explore, imagine, and create without losing themselves in the image.
With Phota Studio and Phota API, developers can build new photo experiences, while photographers and creators can explore a new kind of AI-native editing and generation.
The next photo experience starts here!
3
7
765
Start creating with Phota Studio: studio.photalabs.com and share with us your photos and stories!
Read more in the blog post: news.photalabs.com/blog/the-…
182
Mengwei Ren retweeted
If Harmonize is going a bit too hard (especially on skin), Blend If and Opacity tweaks can help a lot! ✨
Mengwei Ren retweeted
First unveiled as early research at #AdobeMAX last year, @Photoshop’s new Harmonize feature can turn hours of editing into minutes! Kudos to the @AdobeResearch and Photoshop Engineering teams! adobe.ly/4lxiXXs
Mengwei Ren retweeted
This is nuts! Harmonize just landed in the Photoshop beta and compositing will never be the same 🤯
Remember #ProjectPerfectBlend from last year's #MAXSneak? Harmonize is in Photoshop beta today!





















