KEKeras
Keras is a high-level deep learning API that enables fast experimentation with neural networks, running on top of TensorFlow and providing an intuitive interface for building and training models.
Models & Modalities
Foundation models, model toolkits, and multimodal capabilities.
TrackedUnavailableArchivedInactive
Foundation model families and model releases.
KE
PAPaddlePaddle
An open-source deep learning platform developed by Baidu, providing a comprehensive ecosystem for machine learning and deep learning research and production.
UTutopia
An open-source enterprise world model from DeepLethe: a bitemporal knowledge graph that learns passively from your material, keeps ontology and time awareness in the base layer, and deploys offline as a single Rust binary plus Postgres.
Tooling for model conversion, quantization, and packaging.
DEDetectron2
Facebook AI Research's next-generation object detection and segmentation library, offering state-of-the-art algorithms and a rich model zoo.
HUHugging Face Transformers
The model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal, for both inference and training.
Cross-modal modeling for text, image, audio, and video.
CHChandra
Chandra is a high‑accuracy OCR model that converts images and PDFs into structured outputs with layout information.
ELElevenLabs UI
ElevenLabs UI is a component library and custom registry built on top of shadcn/ui to help build multimodal agent interfaces faster.
LELeRobot
An open-source robotics library providing datasets, pretrained policies and simulation environments for reproducible robot learning and deployment.
LILightX2V
LightX2V provides lightweight image-to-vector models and tooling for efficient visual feature extraction and vector retrieval in resource-constrained environments.
OLolmOCR
A toolkit for linearizing PDFs and image-based documents into readable plain text and Markdown, aimed at LLM dataset creation and large-scale document processing.
PAPaddleOCR
PaddleOCR is a lightweight, high-performance open-source OCR toolkit that supports 100+ languages and converts images or PDFs into structured data.
VLvLLM-Omni
A framework for high-performance, cost-efficient inference and serving of omni-modality models across text, image, video, and audio.
Speech-to-text, text-to-speech, and audio understanding.
AUAutoSubs
Generate accurate, editable subtitles locally or integrated with DaVinci Resolve.
COCosyVoice
Multilingual, high-quality streaming TTS / speech generation toolkit supporting zero-shot cloning and low-latency generation.
FIFish Speech
State-of-the-art open source text-to-speech system with voice cloning capabilities, supporting multiple languages with natural-sounding output.
GEGenMedia Creative Studio
GenMedia Creative Studio is a demo web application built on Vertex AI showcasing image, video, audio, and text-to-speech generation capabilities.
GPGPT-SoVITS
GPT-SoVITS is an open-source few-shot voice conversion and TTS WebUI with cross-lingual inference and production-friendly tooling.
HAHandy
A free, open-source, extensible offline speech-to-text desktop application that runs Whisper and Parakeet models locally.
MOMockingBird
An open-source voice cloning and real-time speech generation toolkit that can clone a speaker from a short sample and synthesize arbitrary speech.
NOnoScribe
A local-first audio transcription and editing tool for qualitative research and journalism, built on Whisper and Pyannote.
OPOpenAI Whisper
Robust speech recognition via large-scale weak supervision, supporting transcription and translation across 100+ languages with state-of-the-art accuracy.
TETEN Framework
An open-source framework and ecosystem for real-time, multimodal conversational voice and agent applications.
VIVibe
A privacy-first, cross-platform audio/video transcription tool that supports fully offline operation and batch processing.
VIVibeVoice
Explore VibeVoice, a cutting-edge TTS framework for long, expressive audio synthesis. Ideal for research, media prototyping, and academic evaluation.
VOVoicebox
Open-source AI voice studio for voice cloning, dictation, and audio creation with a modern web interface.
VOVosk API
Vosk API provides offline speech recognition for Android, iOS, Raspberry Pi and servers with bindings for Python, Java, C# and Node.
WHwhisper.cpp
whisper.cpp is a high-performance local Whisper implementation for speech recognition across edge devices and desktop platforms.
Image/video generation models and creative pipelines.
AWAwesome Image & Video Prompts
An open collection of more than 2,200 copy-ready prompts for the leading AI image and video models (GPT Image, Nano Banana, Seedance, Kling, Veo, Wan, MiniMax), each quoted verbatim from its source and shown next to the real output it produced. It also includes agent recipes for editing video with ffmpeg, with the full set searchable in an online gallery.
COComfyUI
A node-based visual workflow builder for Stable Diffusion, enabling graphical assembly and debugging of image-generation pipelines.
DEDeep-Live-Cam
Deep-Live-Cam is an open-source real-time face swap and avatar tool that runs offline for creators and streamers.
HUhuggingface diffusers
Diffusers: a modular toolbox for state-of-the-art pretrained diffusion models for image, audio and 3D generation, suitable for inference and training.
HYHyperframes
Write HTML, render video. Built for AI agents to programmatically create videos from code.
LTLTX-2
Official Python inference and LoRA trainer package for LTX-2, the first DiT-based audio-video foundation model that generates synchronized audio and video in one model, from Lightricks.
OPOpen Generative AI
Open-source alternative to AI video platforms with 200+ models including Flux, Midjourney-style generation, and video creation studio.
OPOpenMontage
The first open-source, agentic video production system that turns an AI coding assistant into a full video studio, handling research, scripting, asset generation, editing, and final composition.
No projects match the current filters.