Today in Generative Media

Oscars OK AI with caveats; Japan mulls AI Ghibli ban; Teaching AI for animation

News and Opinion

• Oscars OK the Use of A.I., With Caveats (New York Times)

• Japanese Lawmakers Are Considering Making AI-Generated Studio Ghibli Images Illegal (HypeBeast)

• Educating Artists about AI in Animation (Animation Magazine) How five higher education courses in different universities are teaching students about new applications of artificial intelligence in their fields.

• Can AI Be Creative? The Next Wave of Tech Is a Tipping Point for Hollywood (MSN)

• Anthropic just analyzed 700,000 Claude conversations — and found its AI has a moral code of its own (VentureBeat)

• Beware the Obsequious AI Assistant (Psychology Today)

• AI isn't ready to do your job (Business Insider)

Software

• Today we launch Reve Image — and it’s the best image model in the world 🥇 (LinkedIn)

• Gemini app rolling out Google Photos integration on Android (9to5Google)

• Dia is a 1.6B parameter text to speech model created by Nari Labs. ... You can condition the output on audio, enabling emotion and tone control. The model can also produce nonverbal communications like laughter, coughing, clearing throat, etc. (GitHub)

Research

• Seedream 3.0 Next-Gen Text-to-Image Model (project page)

• EDGS: Eliminating Densification for Efficient Convergence of 3DGS (project page)

• SkyReels-V2: Infinite-length Film Generative Model (arXiv)

• Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models (arXiv)

• High-fidelity 3D Object Generation from Single Image with RGBN-Volume Gaussian Reconstruction Model (arXiv)