Skip to content
explainroo

Guides · 33 articles

AI models explained

How modern AI models work, in plain words: language models, tokens and context windows, diffusion and video models, multimodal models, speech, and running models yourself.

How Do AI Video Models Work?

AI video models turn a text prompt, image, or existing clip into a sequence of video frames. To reduce the amount of data they process, some models first…

4 min read

How Does Sora Work?

Sora is OpenAI’s video-generation model. It turns a written description into a video, and it can also animate a still image or continue an existing clip.

3 min read

Diffusion Models Explained

When an image generator turns a text prompt into a picture, it needs a way to create an image from scratch.

3 min read

Latent Diffusion: How Image and Video Models Save Work

Image and video generators start with noise and repeatedly refine it into a coherent result. Latent diffusion models reduce this work by refining a compact…

3 min read

Video Diffusion Models: From Noise to Moving Pictures

When you ask an AI video generator to turn a prompt into a clip, it must create a scene and show how it changes over time.

3 min read

Multimodal AI: How Models See, Hear and Speak

When an AI system takes a photo, listens to a recording, or answers out loud, it handles more than text.

4 min read

Vision Language Models Explained

When an AI tool answers a question about a photo or writes a caption for an image, it is using a vision-language model, or VLM.

3 min read

World Models: What They Are and Why They Matter

When a robot moves an object or a self-driving vehicle approaches an intersection, it needs to predict what will happen after it acts.

3 min read

How Do LLMs Work?

When you ask a chatbot a question, a large language model (LLM) breaks your text into pieces, uses patterns learned during training to predict what text…

3 min read

What Is a Token in AI?

When you ask a language model to summarize a document or answer a question, it splits the text into small units called tokens.

2 min read

What Is a Context Window?

When you ask an AI language model a question, it can process only a limited amount of information at once.

2 min read

What Are Embeddings?

AI systems compare words, images, and other data by representing them as numbers. An embedding is a list of numbers, called a vector, that represents an…

3 min read

Transformers Explained: The Architecture Behind Modern AI

When an AI model reads a prompt or writes a response, it needs to represent the words and relationships in the text.

3 min read

How Does Text-to-Speech Work?

When a phone reads a message aloud or a screen reader speaks a web page, text-to-speech (TTS) turns written words into audio.

3 min read

How Does Speech Recognition Work?

When you speak to a phone, computer, or voice assistant, speech recognition turns your words into text.

3 min read

How Does AI Image Generation Work?

When you type a description into an image generator, the generator uses your words to guide image creation.

3 min read

Open Source AI Video Models

If you want to generate video on your own hardware or adapt a model to a particular style, open-weight models give you more control than closed…

3 min read

Wan 2.1: The Open Video Model Explained

1 is an openly available model family developed by Alibaba. The family includes related versions for different tasks and hardware limits.

3 min read

HunyuanVideo: The Open Video Model Explained

HunyuanVideo is Tencent’s model family for generating video from text prompts or, in some versions, a starting image.

3 min read

Comparing AI Video Models

Choosing an AI video model depends on what the finished clip needs to do. Some models produce realistic motion and sound.

4 min read

How to Make AI Videos with ComfyUI

To make an AI video in ComfyUI, load a video-generation workflow and choose a compatible model, then describe the clip before running the workflow.

3 min read

Running a Local LLM

If you want an AI assistant to work with private files, run offline, or avoid per-token API fees, you can run a large language model (LLM) on your own computer.

3 min read

Choosing a Local LLM

A local large language model (LLM) generates responses on hardware you control. Many local options are open-weight, meaning you can download their trained…

5 min read

Ollama Tutorial: Run Models on Your Own Computer

If you want to chat with an AI model without sending each prompt to a hosted chatbot, Ollama lets you download and run language models on your own computer.

3 min read

What Is Hugging Face?

People often compare Hugging Face to GitHub for AI: both host projects that others can explore and reuse.

3 min read

What Is OpenRouter?

If you build or use software that sends requests to AI models, OpenRouter gives you one API for accessing models from multiple providers.

2 min read

Open Source AI Models: What You Can Run and Build On

You also become responsible for hardware, licensing, and ongoing operation. Many models described as “open source” are more precisely open-weight: their…

4 min read

Choosing a GPU for AI

For local AI, choose a graphics processing unit (GPU) based on the work you plan to run and the card’s memory.

4 min read

What Is an AI PC?

When you shop for a Windows laptop or desktop labeled “AI PC,” the name usually means it has hardware for running some AI features on the computer.

3 min read

LLM API Pricing Explained

When you use a large language model (LLM) through an API, the provider generally charges for the text the model processes and generates.

3 min read

Claude vs. ChatGPT

If you are choosing an AI assistant for writing, research, coding, or everyday tasks, Claude and ChatGPT both handle a wide range of requests.

3 min read

Claude vs. Gemini

Anthropic makes Claude, and Google makes Gemini. Both answer questions and work with documents. They differ in how they handle long writing, current…

3 min read

ChatGPT vs. Gemini

ChatGPT is a strong all-purpose choice with many features and integrations. Gemini stands out if you use Google apps, need to review long documents or…

4 min read

Videos made with explainroo

A coding agent made each of these with explainroo, from the script to the finished MP4.

Free and open source

Make your own with your AI agent

explainroo lets a coding agent like Claude Code or Codex make narrated explainer videos and product demos. The voice, the word timing and the rendering run on your own computer, with no API key and no cost per video. Optional outside services use your own key.

Copy this into your AI agent

Make me a short explainer video about [your topic]. Use explainroo for it: run npx --yes explainroo docs and follow what it prints.

Getting started Example videos GitHub

Made with explainroo: How explainroo makes a video