Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins

Clip chaining for MiniMax H3 in ComfyUI - motion and audio genuinely continue across joins

NVIDIA Sol-Attn for ComfyUI / Triton kernel on SM89 - SM121, with zero-copy MiniMax H3 nodes: memory-efficient attention, scheduled tau with graph preview, and feed-forward chunking. Measured 1.14–…

sparkDash ⚡ — Multi-DGX Spark Monitoring Dashboard

S3-Compatible Object Storage. A MinIO fork maintained by PGSTY

RenderDoc is a stand-alone graphics debugging tool.

대한민국의 걸그룹 RESCENE(리센느)의 음악방송, 컨텐츠를 한번에 볼 수 있는 모아보기 사이트 입니다.

[SIGGRAPH Asia 2026] Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild

ShotPlan: Cinematic Video Generation with Learnable Planning Token

Convert 2D videos and photos into interactive 3D scenes using Gaussian splatting backends (VGGT, LongSplat, DepthSplat, SHARP, TripoSplat), Rerun, and the SuperSplat editor.

[ECCV 2026] MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code

UE5-based Data Engine used in OmniX

An open ecosystem of parametric human models and perception stacks, starting with GNM Head.

Official implementation paper OmniX: Any-view and Any-time 4D Reconstruction via Feed-forward Trajectory Fields

PoCs and exploits for CVEs discovered by VEGA.

Stealth Chromium engine that stops scrapers and browser agents from getting blocked, with one line of code change.

LLM extensions for Sphinx Documentation

Skill that audits and rewrites content to remove AI writing patterns. Use it with your favorite agents including Claude Code, OpenClaw, Codex, and Hermes.

Code release for "i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models"

macOS terminal tool to benchmark disk read/write speed

An enhanced tool for CodexApp, striving to make Codex better to use and more comfortable 一个CodexApp的增强工具，努力让Codex变得更好用更舒服

An open-source audio wake word (or phrase) detection framework with a focus on performance and simplicity.

Ideogram 4: Open image model at the forefront of design

Miso TTS is an 8 billion, highly emotive text-to-speech model

Self-hosted AI workspace.