Mark Boss (@markb_boss) 's Twitter Profile
Mark Boss

@markb_boss

I’m a researcher at Stability AI with research interests in the intersection of machine learning and computer graphics

ID: 60343702

linkhttps://markboss.me calendar_today26-07-2009 16:53:33

267 Tweet

1,1K Followers

213 Following

Mark Boss (@markb_boss) 's Twitter Profile Photo

This a super cool use case for SPAR3D - on the fly asset generation. Also super cool to see what you can do with gradio demos :)

Stability AI (@stabilityai) 's Twitter Profile Photo

Introducing Stable Virtual Camera: This multi-view diffusion model transforms 2D images into immersive 3D videos with realistic depth and perspective—without complex reconstruction or scene-specific optimization.

Jensen (Jinghao) Zhou (@jensenzhoujh) 's Twitter Profile Photo

Hi there, Stable Virtual Camera is out everywhere now! Working with my amazing co-developer Hang Gao and the incredible team Vikram Voleti, Aaryaman "Jam" Vasishta, Chun-Han Yao, Mark Boss, Philip Torr, Christian, and Varun Jampani has been such a blast and in a million ways dream

AK (@_akhaliq) 's Twitter Profile Photo

Stability AI just dropped Stable Virtual Camera on Hugging Face a generalist diffusion model designed to address the exciting challenge of Novel View Synthesis (NVS). With just one or a few images, it allows you to create a smooth trajectory video from any viewpoint you desire.

MrNeRF (@janusch_patas) 's Twitter Profile Photo

Stable Virtual Camera: Generative View Synthesis with Diffusion Models Hint: Check the project website. It is awesome! Contributions: 1. A training strategy for jointly modeling large viewpoint changes and temporal smoothness. 2. A two-pass procedural sampling method for

Chris make some 3D scans (@chrisatkiri) 's Twitter Profile Photo

When I woke every day, so many new things hit my head. Stable Virtual Camera (github.com/Stability-AI/s…) from stabilityAI can transfer a single image to a trajectory video in very high quality. Of course, the model cannot be 100% perfect. But the improvement speed is crazyyyy. Here

Jensen (Jinghao) Zhou (@jensenzhoujh) 's Twitter Profile Photo

Glad to see that Stable Virtual Camera is now trending #1 among Huggingface Image-to-Video models and #10 among all demos! Keep it up, folks! 💪

Glad to see that Stable Virtual Camera is now trending #1 among Huggingface Image-to-Video models and #10 among all demos! Keep it up, folks! 💪
Jensen (Jinghao) Zhou (@jensenzhoujh) 's Twitter Profile Photo

Not just virtual. Visceral. Stable Virtual Camera simulates exposure through the eye of experience. 📸: Photo by Mark Boss - unsplash.com/photos/a-view-…

Lucky Iyinbor (@luckyballa) 's Twitter Profile Photo

So Flow Matching is *just* xt = mix(x0, x1, t) loss = mse((x1 - x0) - nn(xt, t)) Nice, here it is in a fragment shader :) shadertoy.com/view/tfdXRM

Mark Boss (@markb_boss) 's Twitter Profile Photo

Amazing project from Ta-Ying. I can highly recommend playing with the gradio demo: huggingface.co/spaces/stabili… I was super impressed that the method even works on non-realistic images.