NVlabs/Sana — SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion…

This is a stars post classified by Jev as Models & inference (a tool drop), kept by the Stars Radar because it carries real work, not commentary.

NVlabs/Sana — SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

Posted by NVlabs (0 followers) 2 h ago · 9.2k likes · 9.2k views · view the original post on X. Kept by the Stars Radar as Models & inference. Tools mentioned: Sana.

More stars work like this

• microsoft/BitNet — Official inference framework for 1-bit LLMs — @microsoft
• Tiiny-AI/PowerInfer — High-speed Large Language Model Serving for Local Deployment — @Tiiny-AI
• xinyao27/jevonian — One local endpoint. The right model for every turn — enforced in… — @xinyao27
• muellerberndt/cadence — A brain that learns from live experience. System 1 by default:… — @muellerberndt
• BerriAI/litellm — The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+… — @BerriAI
• mizorewww/laya-mlx — Native MLX runtime for Laya typed decision models — 7–14 ms short… — @mizorewww
• anomalyco/models.dev — An open-source database of AI models. — @anomalyco
• JustVugg/colibri — Run frontier MoE models on hardware you already own — pure C, zero… — @JustVugg

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 277 posts from 1 X accounts over the last 365 days, 277 tools, 10 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-10-06 08:34 UTC. Full method.