关键词 "Size recommendations" 的搜索结果， 共 19 条, 只显示前 480 条
Typecast is an AI voice generator with 400+ realistic voices for creating lifelike audio content.
PlayHT is an AI Voice Generator platform with over 600 voices in multiple languages.
Rate and discover games with Minimap for personalized gaming recommendations.
Pixelied is a versatile and free graphic design tool with various features and a large library.
Create, edit, and grow content with Kapwing's collaborative online platform.
Create stunning product photos with insMind AI Generated Fashion Momels. Choose AI models from female, male, diverse skin stones, hari colors, and body sizes. Face swap to change the home-made photos
AI-powered video editor and graphic design tool for all platforms.
Easy online photo editor with a wide range of features and tools.
mcp-ffmpeg: resize videos, extract audio.
This project is a proof of concept for running a local-first multi-agent system using: 🤖 Local LLMs via Ollama 🧩 Simple function/tool-call detection using <tool_call>... 🔍 Brave Search API or optional
Create an MCP Server to interact with Spotify, LastFM and the internet to collate music data and make recommendations.
🧠 An adaptation of the MCP Sequential Thinking Server to guide tool usage. This server provides recommendations for which MCP tools would be most effective at each stage.
MCP server for generating human face images with various shapes and sizes
<p>Overview Spark-TTS 是由出门问问（Mobvoi）联合多所顶尖学术机构（如香港科技大学、上海交通大学）最新推出的新一代语音合成模型，其核心创新在于BiCodec编码技术和与文本大模型的结构统一性，利用大型语言模型 (LLM) 的强大功能实现高度准确且自然的语音合成。</p> <p>Spark-TTS is an advanced text
BILIVE 是基于 AI 技术的开源工具，专为 B 站直播录制与处理设计。工具支持自动录制直播、渲染弹幕和字幕，支持语音识别、自动切片精彩片段，生成有趣的标题和风格化的视频封面。BILIVE 能自动将处理后的视频投稿至 B 站，综合多种模态模型，兼容超低配置机器，无需 GPU 即可运行，适合个人用户和小型服务器使用。 1. Introduction Have you notice
MMaDA（Multimodal Large Diffusion Language Models）是普林斯顿大学、清华大学、北京大学和字节跳动推出的多模态扩散模型，支持跨文本推理、多模态理解和文本到图像生成等多个领域实现卓越性能。模型用统一的扩散架构，具备模态不可知的设计，消除对特定模态组件的需求，引入混合长链推理（CoT）微调策略，统一跨模态的CoT格式，推出UniGRPO，针对扩散基础模型的统
Path is a team of more than 300+ image-editing experts and graphic designers who provide professional Photoshop services to e-commerce businesses, product photographers, and small and medium-sized bus
小红书hi lab（Humane Intelligence Lab，人文智能实验室）团队首次开源文本大模型 dots.llm1。 dots.llm1是一个中等规模的Mixture of Experts (MoE)文本大模型，在较小激活量下取得了不错的效果。该模型充分融合了团队在数据处理和模型训练效率方面的技术积累，并借鉴了社区关于 MoE 的最新开源成果。hi lab团队开源了所有模型和必要的训练
概述 LandingAI Agentic 文档提取API 从视觉复杂的文档（如表格、图片和图表）中提取结构化数据，并返回具有精确元素位置的分层 JSON。 这个 Python 库包装了该 API 以提供： 长文档支持——一次调用即可处理 100 多页 PDF 自动重试/分页——处理并发、超时和速率限制 辅助实用程序——边界框代码片段、可视化调试器等 特征
只显示前20页数据，更多请搜索
Showing 409 to 427 of 427 results
