AI Image Generation: Visual Artistry with Midjourney, Adobe Firefly, and DALL-E3
summary
Compares Midjourney, Adobe Firefly, and DALL-E3 with concrete before/after images across versions, explains diffusion models as the technical leap, and demonstrates live features: prompt→image, inpainting, zoom‑out, and reusing a character across shots. Claims photorealism by MJ v5–v6 and Firefly v2–v3, notes persistent hand/face artifacts, and quantifies a workflow win — 100 goblins in an hour for concept art — while showing a live Discord-based generation that succeeds visually and raising concrete ethics examples about fake news and training data.
AI-written summary · about
chapters (6)
- 0:00AI image generation tools
- 4:11History of image generation
- 18:09Evolution of AI models
- 23:11MidJourney vs Firefly
- 34:34Advanced features & uses
- 41:42Ethical concerns & demo
related talks
36mArt in the Age of Algorithms
25mDecoding Algorithmic Artistry: Visual Generative AI
57mAImages - how neural networks will affect the production of games
33mAI Images: Redefining Quality with Innovation
28mBeyond DALL-E: Advanced Image Generation Workflows with ComfyUI
25mDesigning at the speed of AI
33mThe Dawn Of Universal Creativity
50mWelcome to the Latent Dystopia