We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
- diffusion-models
- high-resolution
- sparse-attention
- video-generation
47,133 repositories indexed
73–96 of 156 · Most stars
We propose Prism, a dynamic sparse attention framework for natively training joint video-audio generation models at 2K.
Entity Relation Diagrams generation tool
Open-source AI video replacement workflow by TEIN. Combine depth maps, SAM segmentation, face meshes, and audio processing to replace characters and objects with Seedance. Includes a local web UI to prepare inputs, review masks, preview generations, and export with original audio.
Evaluation code for various unsupervised automated metrics for Natural Language Generation.
The Prime Cross Site Request Forgery (CSRF) Audit and Exploitation Toolkit.
Pika H3 Flex: video and audio generation inference
A modular vulnerability scanner with automatic report generation capabilities.
Brian is a free, open source simulator for spiking neural networks.
NFStream: a Flexible Network Data Analysis Framework.
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
TranslatedImage-driven 3D scene generation system. Users provide a reference image and prompt words, and the system generates previewable, replayable, and traceable scene results according to the camera trajectory; official 3D demonstration assets allow direct viewing of color/depth animations and Gaussian point clouds in the browser. Image-driven 3D scene generation system
Next generation Wagtail demo, born in Reykjavík
AssetFurnace: the most complete open-source image-to-3D pipeline (Oct 2026). Prompt or picture → textured, rigged, animated game character, locally on Apple Silicon or NVIDIA. Pixal3D, TRELLIS.2, Hunyuan3D, SF3D, auto-rig and 21 moves. For indie game devs and 3D artists. Free, Apache-2.0.
This Word Does Not Exist
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models
EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluation code.
:spider_web: Gmsh for Python
TranslatedOpenAI-compatible API for Muse.ai with Chat, Image & Video generation. It wraps Muse (muse.ai) via reverse engineering as an OpenAI-compatible interface, supporting chat, text-to-image, text-to-video/image-to-video, multi-account pool rotation, and 48h automatic renewal.
Scenario for Blender: AI images, video, 3D and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later.
🧠+🎧 Build your music algorithms and AI models with the next-gen DAW 🔥
OpenFE: automated feature generation with expert-level performance
TensorFlow Implementation of Unsupervised Cross-Domain Image Generation
GRUV is a Python project for algorithmic music generation.
BLEURT is a metric for Natural Language Generation based on transfer learning.