A robust multimodal system for detecting and rephrasing profanity in both speech and text, leveraging advanced NLP models to ensure accurate filtering while preserving conversational context.
-
Updated
Mar 16, 2025 - Python
A robust multimodal system for detecting and rephrasing profanity in both speech and text, leveraging advanced NLP models to ensure accurate filtering while preserving conversational context.
Open-source weight space editing for small language models. Direct tensor edits, measured hill climbs and a Hugging Face workbench.
Safe SDXL + FLux-Dev Gardio on HF-ZeroGPU (pornmasterPro_realismILV4 + Flux-Dev Uncensored)
5 to 40 min. a day on a blackwell rtx 6000 for free or 9 $ month? Why not?
A Python-based multi-GPU image generation pipeline using Huggingface Diffusers with LoRA (Low-Rank Adaptation) support. This project distributes image generation workloads across all available GPUs on the system leveraging Python multiprocessing to optimize throughput and speed.
Local AI assistant for reviewing suspicious Pakistani notices and messages with MiniCPM, Nemotron-Parse, and Docker CUDA support.
Local-first scam defense for someone you love
Terminal CLI for ZeroGPU — an ultra-fast, compute-efficient inference provider for apps and agents. Purpose-built small and nano models on an edge network, with zero GPU infrastructure, serverless, and auto-scaling built in.
ML Research Assistant — AI-powered research tool with arxiv search, LLM leaderboard, model benchmarks, paper finder, and live AI news feed. Built with Gradio + Qwen2.5-7B.
AI SDK provider for ZeroGPU, a compute-efficient inference provider for apps and agents: purpose-built small and nano language models on an edge network that run the repeatable tasks frontier models shouldn’t, ~10x faster and 50%+ cheaper. Auto-scaling, with zero GPU infrastructure. Plug in and you’re live.
BiRefNet-based AI background removal system with custom mask, structural, alpha, and fine-detail refinement. FastAPI + Gradio deployment.
Hermes Agent Community Microtuned Decentralized Node Network (HACMDN-Net) — 10M to 32B/MoE niche specialists, topological connectors, self-healing distillation, and Open DeSci mesh
Official ZeroGPU nodes for n8n. ZeroGPU is a compute-efficient inference provider for apps and agents — purpose-built small and nano language models on an edge network that run the repeatable tasks frontier models shouldn’t, ~10x faster and 50%+ cheaper. Auto-scaling, with zero GPU infrastructure. Plug in and you’re live.
Transform Product Vision Board JSON into professional Mermaid diagrams with AI
Plant leaf image classifier with a React interface, FastAPI/PyTorch inference, 38 leaf categories, and a free Hugging Face demo.
Advance Passport Size Photo Studio V10 — Cloud-Native AI Virtual Try-On (CatVTON AnatomicalBodyFit™), BRIA RMBG-2.0 Matting, 12-Zone Spatial Relighting & True 8K Super-Resolution on Gradio 6.32
Agent toolkit for building, deploying, and orchestrating Hugging Face Spaces and models
Flux-Krea-multi-GPU-Pool is a multi-GPU image generation tool using Flux.1-Krea with Super Realism LoRA weights and multiprocessing for fast, scalable results with configurable prompts 🐙
Hermes Agent skill & CLI toolkit for building JIT Gradio 6 apps, modular daggr/gr.Workflow pipelines, and Hugging Face Spaces
Farm advisory assistant in English, Hindi and Kannada: RAG over the TNAU crop guide with BharatGen AgriParam and AI4Bharat IndicTrans2. CS3235 case study.
To associate your repository with the zerogpu topic, visit your repo's landing page and select "manage topics."