Today in Generative Media

AI Photoshop; Google's AI for product images; the AI writing tool everyone hates

• A.I. Photoshopping Is About to Get Very Easy. Maybe Too Easy. (New York Times, paywalled)

• I turned my vacation photos into nightmares with Photoshop’s new generative AI tool (The Verge)

• Google’s new generative AI tool can help sellers jazz up their product images (The Verge)

• I tried the AI novel-writing tool everyone hates, and it’s better than I expected (The Verge)

• Here is my journey on connecting multiple AI generated rooms together (Jussi Kemppainen)

• TUTORIAL: Generate expressions and video lipsyncs of AI characters (using Google Colab and Adobe Express) (Twitter)

• There's now a usable implementation of DragGAN (that cool demo showing the lion opening and closing its mouth) (Twitter)

• Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence (arXiv)

• Control-A-Video: Controllable Text-to-Video Generation with Diffusion Models (arXiv). Project page here.