Spectrum-based acceleration for ComfyUI’s native MiniMax H3 audio-video model. Forecasts post-transformer features with Chebyshev ridge regression to skip selected transformer evaluations, with ada…

DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark

FlashMemory DS-V4 Retriever: a lightweight retriever that sparsifies DeepSeek-V4 CSA KV-cache. Weights available on Hugging Face.

DeepSeek V4 Flash 0731 on 8x NVIDIA DGX Spark: deployment, reproducible benchmarks, optimization profiles, and sanitized evidence.

DeepSeek-v4-Flash-One-DGX-Spark - DwarfStar 4 Engine

Entrpi/ds4, a Blackwell CUDA perf fork of antirez/ds4 on NVIDIA DGX Spark: one-command install, ~3x upstream prefill, ~1.5x decode, DSpark, and full continuous batch support

Deploy DeepSeek V4 Flash (MoE reasoning model) on dual DGX Spark nodes with 1M token context, InfiniBand, and FP8 KV-cache

DeepSeek-v4-Flash 0731 recipe for 2x DGX Sparks

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

MoVerse: Real-Time Video World Modeling with Panoramic Gaussian Scaffold

Official Implementation of SCAIL-2: Unifying Controlled Character Animation with End-to-end In-Context Conditioning

ESM / jQuery plugin for creating video backgrounds from YouTube, Vimeo or video file links.

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

A Python framework for AI-driven character animation using neural networks.

Official Implementation of MultiWorld: Scalable Multi-Agent Multi-View Video World Models

Desktop app to generate 3D models from images or prompt using local AI — runs entirely on your GPU

Create and share 3D architectural projects.

[SIGGRAPH 2026] AniGen: Unified S^3 Fields for Animatable 3D Asset Generation

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Instruct-NeRF2NeRF: Editing 3D Scenes with Instructions (ICCV 2023)

[EMNLP'24] CharacterGLM: Customizing Chinese Conversational AI Characters with Large Language Models

[SIGGRAPH'24] CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

Your AI Game Dev Hub. The ultimate resource hub for AI-powered game development tools. Discover cutting-edge LLMs, World Model, Agent, Code, Image, Texture, Shader, 3D Model, Animation, Video, Audi…

TripoSR: Fast 3D Object Reconstruction from a Single Image

✨ An advanced 3D Gaussian Splatting renderer for THREE.js

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

🎬 2000+ curated Seedance 2.0 video generation prompts — cinematic, anime, UGC, ads, meme styles. Includes Seedance API guides, character consistency tips, and advanced video workflows.