SANA-WM, a 2.6B open-source world model for 1-minute 720p video (nvlabs.github.io) | HN Screenshots

YHacker Newsscreenshots

Screenshot of nvlabs.github.io: SANA-WM, a 2.6B open-source world model for 1-minute 720p video

First screen, captured 5 months ago.

Looks similar

Screenshot of penghtyx.github.io: Era3D: High-Resolution Multiview Diffusion Using Efficient Row-Wise Attention

Era3D: High-Resolution Multiview Diffusion Using Efficient Row-Wise Attention (penghtyx.github.io)

105 points by jasondavies 2 years ago | 9 comments

Screenshot of zeyuet.github.io: AudioX: Diffusion Transformer for Anything-to-Audio Generation

AudioX: Diffusion Transformer for Anything-to-Audio Generation (zeyuet.github.io)

137 points by gnabgib 1 year ago | 16 comments

Screenshot of haidog-yaqub.github.io: EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer

EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer (haidog-yaqub.github.io)

73 points by blacktechnology 2 years ago | 10 comments

Screenshot of arxiv.org: Efficient LLM inference solution on Intel GPU

Efficient LLM inference solution on Intel GPU (arxiv.org)

87 points by PaulHoule 2 years ago | 20 comments

Screenshot of instantsplat.github.io: InstantSplat: Sparse-View SfM-Free Gaussian Splatting in Seconds

InstantSplat: Sparse-View SfM-Free Gaussian Splatting in Seconds (instantsplat.github.io)

85 points by smusamashah 2 years ago | 2 comments

Screenshot of stateofutopia.com: MicroLLM Lab – Try 7 tiny LLM's in the browser

MicroLLM Lab – Try 7 tiny LLM's in the browser (stateofutopia.com)

271 points by logicallee 27 days ago | 99 comments

MicroLLM Lab is a browser-based tool for running, chatting with, and benchmarking small quantized language models locally via WebGPU with no server.

small-language-models webgpu in-browser-inference quantization

Related stories

Screenshot of openwam.stanford.edu: OpenWAM: An Open Framework for Composable World-Action Models

OpenWAM: An Open Framework for Composable World-Action Models (openwam.stanford.edu)

9 points by ilreb 19 days ago | 3 comments

Project page for OpenWAM, a Stanford open framework combining video prediction and robot control via composable world-action models on a causal video backbone.

world-models robotics video-prediction robot-learning

Screenshot of github.com: Nvidia Warp: A Python framework for high performance GPU simulation and graphics

Nvidia Warp: A Python framework for high performance GPU simulation and graphics (github.com)

453 points by jarmitage 2 years ago | 125 comments

GitHub repository for NVIDIA Warp, a Python framework for writing high-performance GPU simulation and graphics code.

nvidia-warp python gpu cuda

Screenshot of github.com: Nvidia NemoClaw

Nvidia NemoClaw (github.com)

356 points by hmokiguess 7 months ago | 234 comments

GitHub repository for NVIDIA NemoClaw, a plugin for secure installation of OpenClaw, licensed Apache-2.0.

nvidia openclaw ai-agents nemoclaw

Screenshot of openai.fm: OpenAI Audio Models

OpenAI Audio Models (openai.fm)

610 points by KuzeyAbi 1 year ago | 285 comments

OpenAI.fm is an interactive demo where developers can try OpenAI's new text-to-speech model with selectable voices, vibes, and scripts.

openai text-to-speech openai-api voice-ai

Screenshot of cnbc.com: Nvidia, Microsoft, Meta warn against overregulating open-weight models

Nvidia, Microsoft, Meta warn against overregulating open-weight models (cnbc.com)

619 points by louiereederson 3 months ago | 279 comments

CNBC article reporting that Nvidia, Microsoft, and Meta signed a letter warning against premature restrictions on open-weight AI models.

open-weight-models ai-regulation nvidia microsoft

Screenshot of stratechery.com: Nvidia's Risky Business

Nvidia's Risky Business (stratechery.com)

325 points by jonbaer 2 months ago | 157 comments

Stratechery article by Ben Thompson analyzing Nvidia's business risks, opening with a historical anecdote about financier Jay Cooke.

nvidia stratechery ai-chips semiconductors