Need to generate image descriptions fast? In this post, we\u2019ll show how to combine .NET 10\u2019s new capabilities with local AI models to create smart AltText \u2014 all in one simple C# file. It\u2019s a fun way to explore what AI can do beyond chat.<\/p>\n
Accessibility matters \u2014 and one simple but powerful way to improve it is by adding AltText<\/strong> to images. Alternative text helps screen readers describe images to visually impaired users, improves SEO, and enhances overall UX. But writing descriptive alt text for every image can be repetitive. That\u2019s where AI comes in!<\/p>\n Local models are a game changer. No rate limits, no cloud latency, and full control over the models you use.<\/p>\n In this sample, we will use Ollama<\/a><\/strong> to run a vision model like gemma3, llama3.2-vision, or mistral-small3.2. These models are great at understanding image content and generating rich natural language descriptions.<\/p>\n ollama run gemma3 Once Ollama is running locally (usually on http:\/\/localhost:11434<\/a>), you can send requests to analyze an image and receive a natural language description.<\/p>\n\n Coming Soon<\/strong><\/p>\n AI Foundry Local will provide similar capabilities with local models. Stay tuned!<\/p><\/div>\n .NET 10 introduced a cool new feature: you can now run a C# file directly with dotnet run. No project scaffolding, no .csproj files \u2014 just clean, script-like execution.<\/p>\n Ref: https:\/\/devblogs.microsoft.com\/dotnet\/announcing-dotnet-run-app\/<\/a><\/p>\n dotnet run app.cs<\/p>\n This is incredibly convenient for scripting tasks like image processing, quick automation, or dev tooling.<\/p>\n Let\u2019s see it in action!<\/p>\n Source: https:\/\/gist.github.com\/elbruno\/4396c9ee3e56d1c86d280faa33b8f9fe<\/a><\/p>\n Save this code as alttext.cs and run it using dotnet run alttext.cs <your image path>. Make sure Ollama is running and the image path is correct.<\/p>\n \/\/ alttext.cs using OllamaSharp;<\/p>\n \/\/ set up the client \/\/ read the image file from arguments \/\/ generate the alt text \/\/ done Tip: If your image is large, consider resizing it before encoding. This reduces request size and speeds up inference.<\/p>\n With .NET 10 and the power of local AI models like Azure AI Foundry Local Ollama, we\u2019re no longer limited to \u201cchat with AI\u201d scenarios. We can now:<\/p>\n Analyze media This is also a great way to learn! Try switching to different local models, modifying the prompt, or adding a few lines to copy the result to your clipboard. These small tweaks help you experiment and understand how to integrate AI into real-world apps.<\/p>\n To go further:<\/p>\n Learn More<\/strong>: Explore the Generative AI for Beginners (.NET)<\/a> repo for hands-on lessons and sample projects. .NET keeps getting more fun, and AI keeps getting more powerful \u2014 especially when you run it locally <\/p>\n Have fun generating smart AltText and making your apps more accessible!<\/p>\n Blog: https:\/\/devblogs.microsoft.com\/dotnet\/announcing-dotnet-run-app\/<\/a> The post Local AI + .NET = AltText Magic in One C# Script<\/a> appeared first on .NET Blog<\/a>.<\/p>","protected":false},"excerpt":{"rendered":" Need to generate image descriptions fast? In this post, we\u2019ll show how to combine .NET 10\u2019s new capabilities with local […]<\/p>\n","protected":false},"author":0,"featured_media":0,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"site-sidebar-layout":"default","site-content-layout":"","ast-site-content-layout":"default","site-content-style":"default","site-sidebar-style":"default","ast-global-header-display":"","ast-banner-title-visibility":"","ast-main-header-display":"","ast-hfb-above-header-display":"","ast-hfb-below-header-display":"","ast-hfb-mobile-header-display":"","site-post-title":"","ast-breadcrumbs-content":"","ast-featured-img":"","footer-sml-layout":"","ast-disable-related-posts":"","theme-transparent-header-meta":"","adv-header-id-meta":"","stick-header-meta":"","header-above-stick-meta":"","header-main-stick-meta":"","header-below-stick-meta":"","astra-migrate-meta-layouts":"default","ast-page-background-enabled":"default","ast-page-background-meta":{"desktop":{"background-color":"var(--ast-global-color-4)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"ast-content-background-meta":{"desktop":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"tablet":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""},"mobile":{"background-color":"var(--ast-global-color-5)","background-image":"","background-repeat":"repeat","background-position":"center center","background-size":"auto","background-attachment":"scroll","background-type":"","background-media":"","overlay-type":"","overlay-color":"","overlay-opacity":"","overlay-gradient":""}},"footnotes":""},"categories":[7],"tags":[],"class_list":["post-2201","post","type-post","status-publish","format-standard","hentry","category-dotnet"],"_links":{"self":[{"href":"https:\/\/rssfeedtelegrambot.bnaya.co.il\/index.php\/wp-json\/wp\/v2\/posts\/2201","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/rssfeedtelegrambot.bnaya.co.il\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/rssfeedtelegrambot.bnaya.co.il\/index.php\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/rssfeedtelegrambot.bnaya.co.il\/index.php\/wp-json\/wp\/v2\/comments?post=2201"}],"version-history":[{"count":0,"href":"https:\/\/rssfeedtelegrambot.bnaya.co.il\/index.php\/wp-json\/wp\/v2\/posts\/2201\/revisions"}],"wp:attachment":[{"href":"https:\/\/rssfeedtelegrambot.bnaya.co.il\/index.php\/wp-json\/wp\/v2\/media?parent=2201"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/rssfeedtelegrambot.bnaya.co.il\/index.php\/wp-json\/wp\/v2\/categories?post=2201"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/rssfeedtelegrambot.bnaya.co.il\/index.php\/wp-json\/wp\/v2\/tags?post=2201"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}} Using Local Models with Ollama<\/h3>\n
\n# or ollama run llama3.2-vision
\n# or ollama run mistral-small3.2<\/p>\n Run C# as a Script with dotnet run app.cs<\/h2>\n
The Full Code Sample<\/h2>\n\n
\n#:package OllamaSharp@5.1.19<\/p>\n
\nvar uri = new Uri(“http:\/\/localhost:11434”);
\nvar ollama = new OllamaApiClient(uri);
\nollama.SelectedModel = “gemma3”;
\nvar chat = new Chat(ollama);<\/p>\n
\nbyte[] imageBytes = File.ReadAllBytes(args[0]);
\nvar imageBytesEnumerable = new List<IEnumerable<byte>> { imageBytes };<\/p>\n
\nvar message = “Generate a complete alt text description for the attached image. The description should be detailed and suitable for visually impaired users. Do not include any information about the image file name or format.”;
\nawait foreach (var answerToken in chat.SendAsync(message: message, imagesAsBytes: imageBytesEnumerable))
\n Console.Write(answerToken);<\/p>\n
\nConsole.WriteLine($”>> Ollama done”);;<\/p>\n What\u2019s Next?<\/h2>\n
\nAutomate content generation
\nBuild offline-capable AI features<\/p>\n
\n Watch & Code<\/strong>: Tune in to the AI & .NET Community StandUp<\/a> to see live demos and join the conversation.<\/p>\n Resources<\/h3>\n
\nGist Code: https:\/\/gist.github.com\/elbruno\/4396c9ee3e56d1c86d280faa33b8f9fe<\/a>
\nOllama: https:\/\/ollama.com<\/a>
\nAI Foundry: https:\/\/aka.ms\/aifoundry<\/a><\/p>\n