ComfyUI nodes for vision-language models: Qwen3-VL, Moondream 3, Florence-2, SmolVLM2, InternVL, Gemma 3, MiniCPM-V. Plus open-vocabulary detection, SAM2/SAM3 segmentation, video temporal reasoning, GGUF via llama.cpp, and hosted LLM/VLM APIs.
- nodes
- comfyui
- custom-nodes
- llava
Extract and Deobfuscate XLM macros (a.k.a Excel 4.0 Macros)
- xlm-interactive-shell
- xlm-deobfuscator
- deobfuscator
- parser
[ECCV22] BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering
- city
- multiscale
- nerf
- neural-rendering
External zigbee component
Generating Images from Captions with Attention
Vāgdhenu — metered Sanskrit/Vedic chant text-to-speech (DiT + BigVGAN). Apache-2.0.
A collection of datasets that pair questions with SQL queries.
[Open-Source Project] Combining MMOCR with Segment Anything & Stable Diffusion. Automatically detect, recognize and segment text instances, with serval downstream tasks, e.g., Text Removal and Text Inpainting
- mmocr
- text-recognition
- segment-anything
- text-detection
The successful integration of Qwen3-VL-Instruct series into the ComfyUI platform has enabled a smooth operation, supporting (but not limited to) text-based queries, video queries, single-image queries, and multi-image queries for generating captions or responses.
OpenICL is an open-source framework to facilitate research, development, and prototyping of in-context learning.
- in-context-learning
- nlp
- language-model
MCP gateway & OAuth MCP servers. LangGraph agent: memory, eval/tracking, PII guard, context trimming. Docker quick start for enterprise agents.
Type hints support for the Sphinx autodoc extension
- autodoc
- python
- sphinx
- typehints
PyTorch implementation of PSPNet segmentation network
AI short drama & micro-drama video generator — turns any idea into a complete short-form drama using multi-agent AI pipeline (screenwriter → storyboard → frames → video). Seedance 2 VIP, Kling 3.0 Pro, Veo 3.1, Sora 2.
Personal-Model First Self Evolving AI Agent 🐘
Gaussian mixture models in PyTorch.
Create textures for 3d models using stable-diffusion and blender
🎭 AI Avatar / digital human platform — upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self-hosted. Claude · Whisper · Chatterbox · MuseTalk.
This tool allows you to perform OSINT and reconnaissance on an organisation or an individual. It allows one to search 1.4 Billion clear text credentials which was dumped as part of BreachCompilation leak. This database makes finding passwords faster and easier than ever before.
:dolphin: :horse: Extensions to Django for use with MySQL/MariaDB
Generalist and Lightweight Model for Text Classification
Pathways for Renewable Energy Planning coupling Short-term Hydropower OperaTion
- renewable-energy
- reservoir-modeling
- hydropower
Full service cloud hosting for the Frappe stack - powers Frappe Cloud
OpenClip - AI-powered highlight extraction for long videos (AI 驱动的长视频精彩时刻提取工具)