AI Visual Generation

日本語版

AI Visual Generation

AI is revolutionizing image and video production. This skill covers all aspects of AI visual generation — from Stable Diffusion, DALL-E, and Midjourney to video generation (Sora) and 3D modeling.

Target Audience

• Creators looking to learn AI image and video generation technologies
• Engineers integrating AI visual generation into their products
• Those interested in AI art and design

Prerequisites

• Foundational AI/​ML concepts
• Basic knowledge of image processing

Learning Guide

00-fundamentals — Image Generation AI Fundamentals

01-image — Image Generation

02-video — Video Generation

03-3d — 3D Generation

Quick Reference

AI Image Generation Service Comparison:
  Midjourney:        Highest quality, Discord-based
  DALL-E 3:          Easy API integration, ChatGPT integration
  Stable Diffusion:  Open source, fully customizable
  Adobe Firefly:     Commercially safe, Adobe integration
  Flux:              Latest open model, high quality

References

1. Rombach, R. et al. "High-Resolution Image Synthesis with Latent Diffusion Models." CVPR, 2022.
2. OpenAI. "DALL-E 3." openai.com, 2024.
3. Stability AI. "Stable Diffusion." stability.ai, 2024.