Mark Boss

3 Sept

Our entire research team at Stability AI will be at ECCV next week! 👋 If you’d like to chat about our research, hear what we’re working on, or learn about open roles, send me a DM. We’re hiring!

Mark Boss reposted

Giorgos Kordopatis-Zilos

@gkordo.bsky.social

15 Oct 2025

🌺 Just 4 days to go! Join us in Honolulu for the Instance-Level Recognition and Generation Workshop at #ICCV2025 🏝 🗓️ Oct 19, 8:30am–12:30pm 📍 Room 306 A We’ll have amazing keynotes, plus oral and poster sessions featuring accepted and invited papers. Don’t miss it! ilr-workshop.github.io/ICCVW2025/

Happy to announce: ReSWD. Sliced Wasserstein Distances are quite powerful, but they perform a Monte Carlo (MC) integration (over random directions). During an optimization this can lead to noisy gradients due to variance. Project page: reservoirswd.github.io

View full thread

huggingface.coReSWD - a Hugging Face Space by stabilityaiCreate images using color matching and guidance features. Upload your reference images and get generated images that match the colors and styles.

Thanks to my co-authors Andreas Engelhardt, Simon Donné, Varun Jampani Also check out the HF demo huggingface.co/spaces/stabi..., the code github.com/Stability-AI..., and the explainer youtu.be/ckcSgf0s-jI

Few examples from the demo. You can generate various styles from a single prompt. You can either pick semantic matching images, or not and get unexpected results. [1] unsplash.com/photos/a-boa... [2] unsplash.com/photos/mount... [3] unsplash.com/photos/man-i... [4] unsplash.com/photos/macro...

Variance in MC is quite common in computer graphics so we combined ReSTIR -- more precisely the weighted reservoir sampling -- with SWD to keep more impactful random directions in the optimization.

This can be used for multiple applications such as color matching or diffusion guidance. Here, we showcase the diffusion process of generating a medieval house with the reference to the right.

I’m at CVPR this week! Looking forward to connecting and discussing all things graphics, 3D, and gen AI. I'll be presenting 3 papers—stop by and chat!

View full thread

marblecontrol.github.ioMaterial Editing in CLIP SpaceMaterial Editing in CLIP Space

3️⃣ MARBLE: Edit materials effortlessly using simple CLIP feature manipulation, supporting exemplar-based interpolation or parametric edits across various styles. Check it out: marblecontrol.github.io

ai4cc.netAI for Content Creation Workshop

11 June 2025

I’ll also be sharing these and other works at the AI4CC workshop on the 12th at 11:00. ai4cc.net

I’m at CVPR this week! Looking forward to connecting and discussing all things graphics, 3D, and gen AI. I'll be presenting 3 papers—stop by and chat!

stable-fast-3d.github.ioSF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination DisentanglementSF3D generates high quality 3D assets from a single input image.

1️⃣ SF3D: Generate textured, UV-unwrapped 3D assets with additional materials incredibly fast (<0.3s)! More details here: stable-fast-3d.github.io

spar3d.github.ioSPAR3DSPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

2️⃣ SPAR3D (follow-up to SF3D): Integrates a fast point diffusion module, enhancing depth, backside modeling, and enabling easier editing. Project page: spar3d.github.io

Mark Boss reposted

Zhenjun Zhao

@ericzzj.bsky.social

20 Mar 2025

Stable Virtual Camera: Generative View Synthesis with Diffusion Models Jensen (Jinghao)Zhou, Hang Gao, Vikram Voleti, @adyaman.bsky.social, Chun-Han Yao, @markboss.bsky.social, @philiptorr.bsky.social, Christian Rupprecht, Varun Jampani arxiv.org/abs/2503.14489

stability.aiIntroducing Stable Point Aware 3D: Real-Time Editing and Complete Object Structure Generation — Stability AIStable Point Aware 3D (SPAR3D) introduces real-time editing and complete structure generation of a 3D object from a single image in less than a second.

8 Jan 2025

Happy to announce SPAR3D! A fast <1s single image to 3D reconstruction model that combines the best from diffusion and regression models by leveraging a point diffusion module to perform a fast initial point cloud. This aids 3D understanding for the mesh estimation stability.ai/news/stable-...

8 Jan 2025

One neat implication is that we can edit the point cloud to fix missing features or wrong scaling. We even created a small gradio component for simple edits in the demo (pypi.org/project/grad...)

huggingface.coStable Point-Aware 3D - a Hugging Face Space by stabilityaiDiscover amazing ML apps made by the community

8 Jan 2025

Check out the HF demo to test the model: huggingface.co/spaces/stabi.... The model (huggingface.co/stabilityai/...) is also available with code and Comfy Nodes github.com/Stability-AI.... We also have a project page available at spar3d.github.io

Mark Boss reposted

Ravid Shwartz Ziv

@shwartzzzivravid.bsky.social

25 Nov 2024

Looking at ICLR submissions with the lowest score - What a work of art! 🧵

Mark Boss reposted

Jon Barron

@jonbarron.bsky.social

22 Nov 2024

I used 📍🔗 emojis to maximize Twitter/Bluesky parity in my profile. This is definitely pointless, but it's fun.