Apps tagged with 'ai-model'

Qwen Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

As a fully open language model, Apertus allows researchers, professionals and enthusiasts to build upon the model and adapt it to their specific needs, as well as to inspect any part of the training process.

State-of-the-art speech models with transcription, translation, and audio understanding, available via API or self-hosted, optimized for cost and efficiency.

Mellum-4b-base is JetBrains' first open-source large language model (LLM) optimized for code-related tasks.

The self-improving AI agent built by Nous Research. It's the only agent with a built-in learning loop — it creates skills from experience, improves them during use, nudges itself to persist knowledge, searches its own past conversations, and builds a deepening model of who...

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

Open-source video model offering superior performance, generating videos efficiently on consumer GPUs and excelling in text conversion and editing.

FLUX 3 is a multimodal foundation model developed by Black Forest Labs for generating and editing images, videos, and audio within a unified architecture. It can produce videos with synchronized native audio up to 20 seconds long from text prompts, images, existing videos, or...

Terminal-native open-source AI coding assistant supporting Mac, Windows, Linux, BSD, with cross-session memory, Git integration, and major LLM API compatibility.

AI assistant with hybrid-attention reasoning, multi-step task handling, lightning chat, deep research, multimodal generation, privacy and cross-platform sync.

Dedicated tool for downloading AI models from Hugging Face, Model Scope, and Civitai on Windows, offering both command line and graphical interface access.

On-device speech recognition tool with real-time transcription, command recognition, speaker identification, low word-error rates, and multi-language support.

Qwen Code is an AI-powered command-line workflow tool designed for developers, adapted from Gemini CLI and optimized for Qwen3-Coder models.

Lyria is Google's latest music generation model. It delivers high-fidelity music and professional-grade audio, across a range of genres and intricate compositions.

A large language model tool developed by AMD, offering superior performance with open access to weights and data, bridging gaps in AI model advancements.

Amazon Nova is a new generation of foundation models with frontier intelligence and industry leading price performance. Generate text, code, and images with natural language prompts.

Supports multi-shot 1080p video generation from text or images, with smooth motion, detailed cinematic visual style, and accurate prompt interpretation.

Creates interactive 2D platformer worlds from images or text prompts, letting users explore and control characters in AI-generated environments trained on video data.

Get instant AI help with any text on your Mac. Highlight text anywhere and improve writing, fact-check information, or explain complex topics without leaving your current app.

Stable Video 4D (SV4D) is a generative model based on Stable Video Diffusion (SVD) and Stable Video 3D (SV3D), which takes in a single-view video of an object and generates multiple novel-view videos (4D image matrix) of that object.

Kaggle is the world's largest data science community with powerful tools and resources to help you achieve your data science goals.

Gemini 2.5 Flash Image, called Nano Banana, is an AI model that generates, edits and transforms images from text prompts, maintains character consistency and allows precise control for asset creation.

Echo combines specialist open-weight models into one system, allocating compute where it improves the result.

1-bit Bonsai 8B implements a proprietary 1-bit model design across the entire network: embeddings, attention layers, MLP layers, and the LM head are all 1-bit. There are no higher-precision escape hatches. It is a true 1-bit model, end to end, across 8.2 billion parameters.

Chandra is a highly accurate OCR model that converts images and PDFs into structured HTML/Markdown/JSON while preserving layout information.