admiredemploy/Kling-Video-Creator-Premium-Bypass: Kling-Crack — Kling AI Video Generator 2026
Kling-Crack — Kling AI Video Generator 2026
Repositories
actualephemer/Sora-AI-Video-Generator-Unlocker: Sora-Crack — OpenAI Sora Video Generator 2026
Sora-Crack — OpenAI Sora Video Generator 2026
ShadowAqueduct/watermark-remover: Purge multi-vendor AI watermarks: clean Unicode text, apply statistical rewrite hooks, and clear C2PA plus metadata from PNG, JPEG, SVG, PDF, DOCX, HTML, and MD.
Purge multi-vendor AI watermarks: clean Unicode text, apply statistical rewrite hooks, and clear C2PA plus metadata from PNG, JPEG, SVG, PDF, DOCX, HTML, and MD.
RawaldinhoJr/PracticeProjectFullStackGenerativeAi: Learning Full stack programming with AI integration using a "choose your own adventure" project
Learning Full stack programming with AI integration using a "choose your own adventure" project
l-nmch/hailo-10h-llm-compiler: Compile your own LLM for the Hailo-10H — an open pipeline from Hugging Face checkpoint to a self-contained HEF, served with hailo-ollama.
Compile your own LLM for the Hailo-10H — an open pipeline from Hugging Face checkpoint to a self-contained HEF, served with hailo-ollama.
rknvv/latent-diffusion-images: Имплементация и обучение DiT + Flow Matching на данных пейзажей LHQ-256
Имплементация и обучение DiT + Flow Matching на данных пейзажей LHQ-256
BennedictQuanTon/AuraLens: AuraLens is an end-to-end multimodal AI lifestyle platform for Gen Z that turns outfit check-ins into curated real-world experiences. Powered by Google Gemini Multimodal Vision, Spatio-Temporal Weather Grounding, and a Generative AI Photobooth Studio.
AuraLens is an end-to-end multimodal AI lifestyle platform for Gen Z that turns outfit check-ins into curated real-world experiences. Powered by Google Gemini Multimodal Vision, Sp...
kamalesh404/VisionCraft: Multi-modal AI workspace — image generation, analysis, OCR, and style transfer in one platform
Multi-modal AI workspace — image generation, analysis, OCR, and style transfer in one platform
kamalesh404/SynthVoice: Real-time voice cloning & text-to-speech — speak in any voice with AI
Real-time voice cloning & text-to-speech — speak in any voice with AI
kamalesh404/NeuralForge: AI model training platform — train, fine-tune, deploy ML models in browser with WebGPU acceleration
AI model training platform — train, fine-tune, deploy ML models in browser with WebGPU acceleration
ziplab/Block3D: Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion
Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion
AhmadJeddi/YOLO-Guide: A practical and technical guide to the YOLO ecosystem — architecture, major versions, independent branches, benchmarks, and the evolution from anchor-based to anchor-free, end-to-end, NMS-free, and open-vocabulary detection.
A practical and technical guide to the YOLO ecosystem — architecture, major versions, independent branches, benchmarks, and the evolution from anchor-based to anchor-free, end-to-e...
aiopshwang/data-analysis-ml-agent-skills: Evidence-first AI agent skills for reliable data analysis, machine learning, model validation, and reproducibility.
Evidence-first AI agent skills for reliable data analysis, machine learning, model validation, and reproducibility.
CALISKAN-EMRE/NSOSYAL: TEKNOFEST 2026 NSosyal İnovasyon — Explainable recommendations, semantic context cards and Turkish AI moderation.
TEKNOFEST 2026 NSosyal İnovasyon — Explainable recommendations, semantic context cards and Turkish AI moderation.
Ericdaany0312/sensenova-mlx: Local MLX text-to-image runtime for SenseNova U1.5 on Apple silicon.
Local MLX text-to-image runtime for SenseNova U1.5 on Apple silicon.
sqzw-x/amane: AI 时代的私人影库
AI 时代的私人影库
faizanjutt473/Loan_Approval-Prediction-Using-Logistic-Regression: Combining a machine learning model with FastAPI for production deployment and Seaborn for data visualization creates a very solid, full-stack data science application.
Combining a machine learning model with FastAPI for production deployment and Seaborn for data visualization creates a very solid, full-stack data science application.
rome-os/rome: Rome is the agentic OS.
Rome is the agentic OS.
sudnie/AI-CFD-DiffusionUNet: Physics-Informed DiffusionUNet for Unsteady and Steady Airfoil Flowfield Reconstruction and Fast CFD Prediction.
Physics-Informed DiffusionUNet for Unsteady and Steady Airfoil Flowfield Reconstruction and Fast CFD Prediction.
alchaincyf/huashu-excel: 数据分析与 Excel 全流程 skill：体检脏表、清洗、对齐需求、分析、对账、交付。让 AI 算出来的数字经得起追问。跨 agent 通用，依赖仅 openpyxl。
数据分析与 Excel 全流程 skill：体检脏表、清洗、对齐需求、分析、对账、交付。让 AI 算出来的数字经得起追问。跨 agent 通用，依赖仅 openpyxl。
Mohmadasif/ML-DataScience-Training: Course materials, practical notebooks, presentations, datasets and projects for AI, Machine Learning and Data Science training.
Course materials, practical notebooks, presentations, datasets and projects for AI, Machine Learning and Data Science training.
itshen/source-reading-methodology: 带 AI 精读大型开源仓库的方法论：四阶段流程、可复用模板、28 条踩坑清单，核心是让每个技术论断都可回溯到源码具体行
带 AI 精读大型开源仓库的方法论：四阶段流程、可复用模板、28 条踩坑清单，核心是让每个技术论断都可回溯到源码具体行
Cripacx/mediagen: AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with EU AI Act content marking.
AI image and video generation skill for Claude Code and other coding agents — Gemini, OpenAI and Kie AI behind one CLI and MCP server, with EU AI Act content marking.