yoni shafir

[Guy Tevet @GuyTvt]

1/ I let @claudeai use the https://t.co/Dppgg8Hbdh API, and the result is an effectively infinite G1 locomotion dataset, rendered in a CAD apartment environment. Here's how:

[yoni shafir @shafir_yoni]

@GuyTvt @claudeai Amazing! You made that so easy

[Gal Davidi @gal_davidi1]

Dimension images used to take a designer. Not anymore.

Introducing Product Dimensions from Bria📸📏
one call turns a product photo + its real measurements into a marketplace-ready dimension image. Seconds, not hours.
Live exclusively on @wavespeed_ai for this week!

[Guy Tevet @GuyTvt]

AnimoFlow is a new open ecosystem for generative character animation, live now at https://t.co/r6kixlAqnm.
It's built on a simple observation: research models in this field are open, impressive, and moving fast, yet almost none of them ever reach animators. >>>

[yoni shafir @shafir_yoni]

@GuyTvt Amazing 🤩

[Misha Feinstein @MishaFein]

Object extraction just got easy - and precise!

Name the object, get a clean cutout. Run it across a scene and chaos becomes a library of reusable assets, each ready for your next pipeline.
Not a finishing touch - an input layer.

Built by @bria_ai_ , live exclusively on @fal

[BRIA AI @bria_ai_]

Introducing Fibo, a next-generation AI image generation and refinement engine by BRIA.

Unlike traditional AI image tools, Fibo constructs visuals layer by layer, giving you full transparency into what changed and why. Simply describe what you want, refine with a prompt, and Fibo handles the rest — whether you're updating a product's color to match your brand, creating polished ad creatives, or iterating on visual concepts in real time.

✅ Image building for full creative control
✅ Intuitive prompt-based refinement — just tell it what to change
✅ Transparent AI: see exactly what was edited and why
✅ Built for ads, marketing, and brand-consistent visuals
✅ Deploy on BRIA's cloud — fast, scalable, and enterprise-ready

Try. Refine. Retry. - Now with Fibo, we finally can.

🔗Edit: https://t.co/NJWj0cj7UM
🔗Generate: https://t.co/LEx8uDetE6

[LTX.io @ltx_io]

🚨 800 FREE CREDITS — 24 HOURS ONLY

We just launched LTX-2.3, our most powerful video model yet. High-res. Fast. Cinematic. Native lip-sync.

Follow + Retweet this post to get 800 credits sent to your DMs.

[Misha Feinstein @MishaFein]

Great to see the community adding #FIBO to MLX

You can see the quantized version optimal for running on you Mac here: https://t.co/Wp1FqEL0TO

Thanks for the great work @filipstrand !

[Misha Feinstein @MishaFein]

Love seeing those FIBO spaces on @huggingface!

FIBO Mashup - Combine any subject, background and style to create your stunning image
try it out: https://t.co/PPqLJpgEnj

What will be the next cool thing?

#briafibo @bria_ai_

[Ron Mokady @MokadyRon]

Big prizes, I wouldn't miss it 🤠

[Misha Feinstein @MishaFein]

Welcome 𝐅𝐈𝐁𝐎!!
The world’s first JSON-native, Open Source T2I model!

Winning both aesthetics and alignment in the benchmarks by being built ground up for 𝒄𝒐𝒏𝒕𝒓𝒐𝒍, 𝒑𝒓𝒆𝒄𝒊𝒔𝒊𝒐𝒏, and 𝒓𝒆𝒑𝒓𝒐𝒅𝒖𝒄𝒊𝒃𝒊𝒍𝒊𝒕𝒚

https://t.co/LMewUlpjzg

The is big!

[Misha Feinstein @MishaFein]

What's better than getting paid for you love doing?

$25K for the best JSON-native creative workflows, tools, and agentic systems built on top of FIBO.

🗓 Deadline: Dec 15 (online)
💰 $25,000 in prizes

Register here:
https://t.co/nlzb8QyUEr

[yoni shafir @shafir_yoni]

@OPatashnik @TelAvivUni Congrats Or 🥳 They are super lucky to have you

[Guy Tevet @GuyTvt]

(1/4)
[HOIDiNi] https://t.co/WPPzG4hrsd
🧵:
Diffusion models are great at generating free-form human motion but tend to break down when objects enter the scene. Human–object interaction demands millimetric precision, and even tiny errors cause hands to float or penetrate surfaces

[yoni shafir @shafir_yoni]

🚨New data alert🚨
📷 Check out our text-to-face-motion dataset: The first to use ARKit, which is easy to capture and already integrated into Unity and Unreal engines📷😍

Now you can easily expand you're dataset by simple capturing more data

[jaron1990 @jaron1990]

1/
What if you could animate a face directly from text?
🎭 Meet Express4D - a dataset of expressive 4D facial motions captured from natural language prompts, designed for generative models and animation pipelines.
🔗https://t.co/okK0JgZMhV
📹👇

[jaron1990 @jaron1990]

1/
What if you could animate a face directly from text?
🎭 Meet Express4D - a dataset of expressive 4D facial motions captured from natural language prompts, designed for generative models and animation pipelines.
🔗https://t.co/okK0JgZMhV
📹👇

[Yotam @yotam_erel]

{1/8}
🧵 When you click a link, have you ever wondered: “Which webpage is actually important?”
Google answered that with PageRank—treating the web as a Markov chain.

Now imagine doing the same…
but for transformer attention.👇

🔗 https://t.co/DqKE6bPI9a

[Ron Mokady @MokadyRon]

Thanks to @linoy_tsaban our office dog Camo got a new @huggingface look 🔥

I guess we will have to open source more now

[yoni shafir @shafir_yoni]

@hila_chefer @bfl_ml Congrats!
They’re lucky to have you