A · BROAD CAPABILITY
Generative AI
Systems that create new content from learned patterns.
07 · Generative & Multimodal AI
How AI Creates Across Different Modalities
This module explains how generative AI creates new content and how multimodal systems work across text, images, audio, video, and other information types.
Separate what a system generates from which modalities it can understand or connect.
The Big Picture · capability and modality map
GENERATIVE AICreates new output
Text Generation
Image Generation
Audio Generation
Video Generation
Code Generation
∩
MULTIMODAL AIWorks across multiple information types
Text · Image · Audio · Video
Exampleimage + text → text answer
text + image → generated image
text + image → generated image
Knowledge Structure
B · GENERATION TYPES
Text Generation
Creates text.
Image Generation
Creates or edits visual content.
Audio Generation · Video Generation · Code Generation
Creates sound, moving visuals, or source code.
C · CROSS-MODAL SYSTEMS
Multimodal AI
Works with more than one type of information.
One AI Experience
USER
Uploads an image and asks a text question.
SYSTEMProcesses image + text.
OUTPUT
Text answer.
Multimodal describes information types; generative describes creation.
Key Distinctions
Generative AI≠LLMBroad creation capability vs language-focused model
Multimodal AI≠Generative AIInformation types vs creation capability
Image Generation≠Diffusion ModelTask capability vs one model family
Code Generation≠Coding AgentGenerated output vs a system that can act
Recommended Learning Path
This is a learning sequence, not a technical dependency chain.
01Generative AI
Creating content.
02Text Generation
Familiar output type.
03Image / Audio / Video
Compare media output.
04Code Generation
Code as generated output.
05Multimodal AI
Connect information types.
Remember the relationship
Generative AI describes creating new content; multimodal AI describes working across multiple types of information, and the two can overlap.