Not all models are built the same! Checkout the images generated by GPT4o 🫠 and Piece-it-Together 👑 using the same set of input images! Piece it Together (PiT) app is live on 🤗 Spaces!

Thanks for sharing our demo for Piece-it-Together🧩 The training and inference code is now available at github.com/eladrich/PiT

nailed a new sweet spot with my HiDream yarn art LoRA 🧶

🔔Excited to announce that #AnyTop has been accepted to #SIGGRAPH2025!🥳 ✅ A diffusion model that generates motion for arbitrary skeletons ✅ Using only a skeletal structure as input ✅ Learns semantic correspondences across diverse skeletons 🌐 Project: anytop2025.github.io/Anytop-page

New job, new reading list 📚 Excited to share I'm joining Runway in its journey to reshape the future of storytelling

🧵1/ Text-to-video models generate stunning visuals, but… motion? Not so much. You get extra limbs, objects popping in and out... In our new paper, we present FlowMo -- an inference-time method that reduces temporal artifacts without retraining or architectural changes. 👇

Artifacts in your attention maps? Forgot to train with registers? Use 𝙩𝙚𝙨𝙩-𝙩𝙞𝙢𝙚 𝙧𝙚𝙜𝙞𝙨𝙩𝙚𝙧𝙨! We find a sparse set of activations set artifact positions. We can shift them anywhere ("Shifted") — even outside the image into an untrained token. Clean maps, no retrain.

Really impressive results for human-object interaction. They use a two-phase process where they optimize the diffusion noise, instead of the motion itself, to get to sub-centimeter precision while staying on manifold 🧠 HOIDiNi - hoidini.github.io

Excited to share our recent work on corrector sampling in language models! A new sampling method that mitigates error accumulation by iteratively revisiting tokens in a window of previously generated text. With: Neta Shaul Uriel Singer Yaron Lipman Link: arxiv.org/abs/2506.06215

Tel Aviv friends: we're hosting an amazing rooftop meetup with a killer speaker lineup (not including me 😅) lu.ma/q8bigfqn

1/ Can we teach a motion model to "dance like a chicken" Or better: Can LoRA help motion diffusion models learn expressive, editable styles without forgetting how to move? Led by Haim Sawdayee, Chuan Guo, we explore this in our latest work. 🎥 haimsaw.github.io/LoRA-MDM/ 🧵👇

Introducing Act-Two, our next-generation motion capture model with major improvements in generation quality and support for head, face, body and hand tracking. Act-Two only requires a driving performance video and reference character. Available now to all our Enterprise

I'm very excited to announce our #SIGGRAPH2025 workshop: Drawing & Sketching: Art, Psychology, and Computer Graphics 🎨🧠🫖 🔗 lines-and-minds.github.io 📅 Sunday, August 10th Join us to explore how people draw, how machines draw, and how the two might draw together! 🤖✍️

Models just want to generalize. For the past years, we’ve been pushing the frontier of controllability in video, releasing new models and techniques for inpainting, outpainting, segmentation, stylization, keyframing, motion and camera control. Aleph is a single in-context model

Aleph: the first letter of a new visual language

Quick invisible camera operator test. Pretty unbelievable. Aleph is as fun as it is impressive.

godmode with Runway Aleph

Now I see the issue! You’re absolutely right, that is a highly unsafe turn. Let me remove the bridge since it is not currently used.

Aleph inherently understands motion making it easy to iteratively manipulate and edit a shot

Always felt like behind the scenes footage is even more magical than the end result