Introducing AI Playground – Intel Gaming Access

更新日期：05/23/2025

AI Playground 是一款适用于英特尔 AI PC 的易于使用的生成式 AI 应用程序套件，由英特尔弧形图形处理器（内置英特尔®酷睿™超强处理器或通过英特尔®弧形™独立图形处理器）提供支持。 AI Playground 以开源项目和打包的 Windows 桌面安装程序的形式提供。

新:支持 Intel Core Ultra 200H 处理器 (ARL-H)。支持用于聊天的 OpenVINO（用于 GPU 或 NPU）和用于文本到视频生成的 LTX Video。AI Playground 还支持 DeepSeek 模型、SD1.5 SDXL、Flux.1-Schnell 和 ComfyUI 工作流、GGUF LLM 支持等。

Download AI Playground:

请注意，虽然安装程序使启动和运行过程变得简单，但这是一款开源测试版软件，其中的组件和版本可能会有冲突。请检查故障排除部分项目自述文件中的已知问题。

安装前，备份上一次安装生成的任何有价值的内容

AI Playground Files 截至 2025 年 5 月 23 日	Version	Links
人工智能游乐场 2.0	2.5.5b	Release Notes \| 下载英特尔酷睿至尊 200H（ARL-H）、英特尔酷睿至尊 200V（LNL）、英特尔酷睿至尊 100H（MTL-H）配备 8GB+vRAM 的 Intel Arc GPU（A 或 B 系列独立 GPU）
Source Code and Repo	2.0.4b	Visit
User Manual	2.0b	下载
Community/Support		First Join 英特尔内部讨论区 AI Playground Discord Channel

What is AI Playground

AI Playground 测试版是一款可免费下载和使用的 AI PC 入门级应用程序，可让人工智能变得简单 Intel AI PC。AI Playground 提供各种易于使用的 AI 功能，可从文本生成图像、增强和风格化图像、从 AI 聊天机器人获取答案，以及利用生产工作流来完成特定的 AI 任务，所有这些都可在您自己的 PC 上本地运行，该 PC 由内置英特尔弧形图形处理器的英特尔酷睿 Ultra 处理器或配备至少 8GB vRAM 的英特尔弧形独立图形处理器提供支持。

Easy To Use:AI Playground 设计简单易用，让您可以快速使用人工智能。AI Playground 会在任务需要模型时提示您，让您下载或提供自己的模型。我们的设置都是根据任务的需要编写和设计的，您不必为了使用人工智能而接受人工智能方面的教育。

All-In-One AI Hub: 无缝切换 创建图像, 图像编辑和一个 聊法学硕士 .AI Playground 将所有功能整合在一个易于使用的体验中。目前，AI Playground 支持 Stable Diffusion 1.5、Stable Diffusion XL、Flux.1-Schnell、LCM Fast LoRAs、Image Upscale、Image to Image Stylization、Inpainting、Outpainting、ChatBot with session history context 和 LLM RAG 功能，允许您从本地计算机获取摘要和搜索内容。

Flexible: AI Playground will provide access to models for all features, and more advanced users can install their favorite models and tweak manual settings, to configure AI Playground to work the way they want it to work.

Local:AI Playground 在本地运行，因此您的提示和输出永远不会离开您的电脑。这为您提供了与人工智能一起工作的内容和输入的隐私和控制权，并使您能够在没有上游实体在您的肩膀上审查您的提示或捕获您的数据和内容的情况下进行控制。

Hardware Optimized:AI Playground 利用强大的英特尔 Xe 内核和 XMX 引擎，采用英特尔 Arc GPU 架构。

Open: AI Playground is also an open-source project where our community can clone, fork or help us address features and capabilities of the main repo.

核心功能

新版人工智能游乐场 2.0

AI Playground 提供了一系列新的解决方案，每种解决方案都扩展了 AI Playground 的功能，并以其模块化架构为基础，在不同版本之间提供价值和功能。

OpenVINO 聊天后台

OpenVINO 现在可以作为聊天后端选项使用。这是 OpenVINO Gen AI 的早期预览版，用于 AI Playground。有了 OpenVINO，您现在可以使用英特尔硬件上性能最强的推理解决方案。

工作流程

在图像生成方面，我们在图像设置中添加了工作流程模式选项。该功能通过整合 ComfyUI 作为图像生成的替代后端引擎来提供图像生成工作流。使用工作流程模式，您可以选择运行已提交到 AI Playground 项目的预定义工作流程。在启动时，我们提供了以下工作流程，让您可以使用更高级别的制作功能和高级图像生成模式

LTX 视频: (新版本 2.2) 现在，在 AI Playground 中使用 LTX Video 解决方案可以将文字转换为视频。描述场景、场景中的人物、他们如何移动以及场景、时间等，并将其转化为动态视频片段。

着色: (新版本 2.2) 现在，你可以直接在 AI Playground 中为黑白老照片着色。从 4 种不同的着色模式中进行选择，赋予老照片新的生命力

工作流程合成图像：左侧为 Flux.1-Schnell 输出，右侧为新的工作流程模式设置

Flux.1-Schnell： 提供了两个使用黑森林实验室 Flux.1-Schnell 模型的工作流程。该模型因其输出质量高、及时性强和支持图像中的文字而广受欢迎，并享有盛誉。使用该工作流程，您可以指定对象的位置、颜色和纹理，以及最终图像中应出现的单词和短语。我们提供了两种工作流程，一种是中等质量的，另一种是高质量的。高质量版本使用了更高精度的模型，与中等质量的工作流程相比，它可能会带来更高质量的输出，以及文字的粘着性和准确性。

线路转照片 HD： 有两种工作流程可用于控制图像的输出，即图像预视觉化和风格化。该工作流程允许你通过参考图像的结构和形式来控制图像的外观。其用途是将简单的线条艺术、设计线框或建筑图纸预视觉化为完全实现的摄影图像，通过文本提示，您可以定义图像中的位置、天气、时间和其他元素，同时保留原始图像的结构和组成。提供两种工作流程。两者都使用 SDXL JuggenautXL 模型来处理高清图像，并使用 Canny ControlNet 模型通过参考图像的结构来控制输出。其中一个还包括一个快速 LCM 模型，类似于默认图像生成中的快速按钮选项。

换脸: 通过该工作流程，您可以使用参考图像样本的相似度来控制文本生成图像的相似度。只需上传一张参考图像 (所有图像保留在本地电脑中)，输入描述输出图像的提示，然后生成。最终生成的图像将以您的提示为指导，但与原始图像十分相似。

工作流程同步:工作流同步按钮允许您下载已提交到公共 AI Playground 资源库的更新或新工作流。这些工作流程可在两个版本之间提供新的功能和特性。

ComfyUI Editor: For users interested in diving into ComfyUI workflows, or those already familiar with ComfyUI, we’ve provided direct access to its workflow editor, allowing users to edit or create workflows for use either directly from ComfyUI or in AI Playground. We encourage and welcome the community created workflows submitted and shared to AI Playground via Pull Requests to our project.

GGUF Support

For the Answer section we’ve added an experimental back-end option, using Llama.cpp with GGUF support. This allows users to run GGUF models directly in AI Playground expanding access to models in this format. When selected, supported GGUF models are pre-populated in the model list. Note this feature has limited features – Retrieval-Augmented Generation (RAG) not currently supported in the alpha release.

Additionally, we’ve included a new Add Model feature. This allows you to insert HuggingFace Model IDs and specific model paths. After adding these models will appear in your model selector, and download them for use, on first run

Runtime Installer

We’ve updated the installation process, to help make it more reliable, expandable and to assist troubleshooting installation issues.

Installation Backend Manager is available at first run of AI Playground and through the Basic Settings

Installation Manager: We’ve included an installation manager, allow users to manage the installation state of various pieces of the application. If any portion is missing or needs fixing, it can be reinstalled using the installation manager.

Single Installer: New to 2.0 is a single installer binary, able to install on all supported hardware including: Intel Core Ultra-H Series 1, Intel Core Ultra Series 2, and Intel Arc Series A and B Series GPUs with 8GB+ of vRAM. Note: as an alpha preview, all systems environments may not be fully tested and functional, back up any previous installs before using.

Backend Restart: We’ve conveniently provided backend end restart buttons for each core component via the Backend Installation Manager, in the Basic Settings of AI Playground. Restarting these backends may improve or restore performance without having to restart AI Playground

UI/UX

Upper: Theme selector. Lower: Resolution Scaler

Themes: With AI Playground 2.0 we’ve added a new Intel Arc theme and provided a means to dress up your AI Playground experience with any of our themes: the original Dark theme, Intel Core Ultra theme, or the new Intel Arc theme.

Resolution scale: Resolution settings can be tricky with Generative AI, because you often need to know what resolutions the model supports. We’ve made this easy with flexibility by adding a resolution scale feature to the Aspect Ratio tool. Now you can set the resolution scale in Megapixels (1 million pixels). And we’ve provided guardrails by setting defaults and boundaries on the resolution you can pick for each image generation mode. Resolution can be freely set using Manual mode.

All Generative AI Features

AI IMAGE GEN:

New in v2.2

LTX-Video Workflow: text to video workflow to generate video clips from text
Colorize Workflow: to bring new colorful life to old photos

From v2.0

Workflow mode powered by Comfy UI backend
Workflow synch: synch with updated workflows, adding new features and capabilities between releases
Flux.1-Schnell Workflows: higher realism, better prompt adherence, with support for generating text in images
Line To Photo Workflows: Generate photo realistic images from simpler line art references
Face Swap Workflow: Control the likeness of an image through a reference image
Aspect Ratio Scale: Smart scale feature setting the megapixel size for generated images

From v1.22

Text to image generation
Default mode: Stable Diffusion 1.5 (Standard) or SDXL (HD) models
Fast LCM mode for SD 1.5 (Standard) or SDXL (HD) models
Smart aspect ratio slider with presets for 36 resolution combinations
LoRA model support
Image upscale to 2X with generative variance
Images to Image stylization with generative influence scale
In-paint generative fix or replace
Generative out-paint beyond image borders
Run alternative models downloaded from HuggingFace or CivitAI
Manual Mode to define values for specific models, schedulers and resolutions

AI CHAT:

New in v2.2

OpenVINO Gen AI back-end for optimized inferencing performance on Intel hardware

New in 2.0

Optional GGUF file support using Llama.cpp (RAG not currently supported)
LLM Single file support (GGUF only)
Add model tool: Add a Huggingface path to add and download LLM models.

From v1.22

PyTorch models support with model selector List (Phi3, Mistral7B, Qwen1-1.5B)
Models quantize to int4 on load to support lower vRAM systems
Session context history
Discussion manager with context history
RAG: Search summarize and get insights from your own documents
Adjust chat font size
Manually add and refresh model list
Hugging Face user access token field to install use restricted models

See AI Playground In Action

Demo Reel

Introduction Video of Core Features

Install Image Checkpoints

For more information, visit the AI Playground project on GitHub, or join our 英特尔内部讨论区 to engage directly with Intel and our Community on AI Playground

通知和免责声明: For information on AI Playground terms, license and disclaimers, visit the project and files on GitHub repo:

License | 通知与免责声明

CREATE Generate stunning images from text in Standard Res, HD or use Manual mode to use alternative models, and advanced features. Adjust quality setting and switch to Fast mode to produce images in a fraction of the time	ENHANCE Take your images to the next level using the Enhance feature. Use Enhance to Upscale images with or without variation, Stylize images, Inpaint and Outpaint images, either from the Create process or images from your own PC.
ANSWER Access to your own AI chatbot. Get answers on generalized knowledge, assistances on writing code, or have the chatbot summarize and get details from text files on your own computer	LEARN MORE AI Playground is a place to get started with your AI journey using Intel Arc GPUs. Join our community, get tips and techniques from our video content or graduate to more specialized AI tool.