ML will transform Creativity forever. Are you ready?
summary
Text-to-image systems like DALL·E and Stable Diffusion are only the start: open source release plus the diffusers library enables community extensions such as a Spider‑Verse style model and Corridor Digital’s AI‑restyled Spider‑Man clip. New techniques (papers like DreamArtist) let a model learn a style from one image and be usable within an hour, making fast, inexpensive customization common. The result is mass accessibility to generate and iterate visuals in seconds, shifting who creates and how creative workflows scale.
AI-written summary · about
chapters (15)
- 0:00Generative AI introduction
- 1:11ML impact on creativity
- 3:59Text-to-image models
- 5:26Community AI customization
- 7:34AI for creative empowerment
- 9:21AI: destroy or democratize art?
- 11:51Job fears and creative boom
- 14:01Radical creative accessibility
- 15:53AI replace or redefine artists?
- 17:20Customized storytelling
- 18:48Open source in creativity
- 19:30Q&A: Traditional artists vs AI
- 20:12Q&A: AI and traditional art
- 22:43Q&A: AI in workflows
- 23:27Q&A: AI-human feedback loop
related talks
01h 27mImage Generation with AI
36mMusic and Art with ML
38mMaking Art with Artificial Intelligence: Artists in Conversation
42mDALL·E and CLIP from OpenAI: a new era in machine learning
33mPrototype ML with Visual Blocks
28mBeyond DALL-E: Advanced Image Generation Workflows with ComfyUI
45mGenerative AI for Image and Video Production
19mAI-Powered Startup Toolkit for a Product Designer