Today in Generative Media
GenAI spams academic journals; SD3 licensing uproar; Adobe updates AI terms of use
News
This Week in AI: Generative AI is spamming up academic journals (TechCrunch)
Licensing Questions Plague Stability AI as SD3 Image Generator Gets Banned (Decrypt)
Adobe's New Terms of Use: A Win for Creators, but AI Concerns Persist. (X)
Opinion: As AI is embraced, what happens to the artists whose work was stolen to build it? (Los Angeles Times)
SIGGRAPH 2024 Technical Papers Awards: Best Papers, Honorable Mentions, and Test-of-Time (SIGGRAPH blog)
AI Artists vs Traditional Artists -- Can They Unite? | Dustin Hollywood at Imagine AI Live | E52 (YouTube)
Software and Data
Meta releases flurry of new AI models for audio, text and watermarking (VentureBeat)
Microsoft drops Florence-2, a unified model to handle a variety of vision tasks (VentureBeat)
OpenAI upgrades DALL-E 3 instead of rolling out GPT-4o's (much better) imaging capabilities (The Decoder)
The best AI video editing software (Creative Bloq)
Augie Studio aims to become the Canva for AI video creation for marketers and enterprise (VentureBeat)
Jupyter notebook for Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image (GitHub)
Research
Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following (CVPR 2024, project page)
MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers (project page)