Today in Generative Media

'My Drama' AI companions; AI backlash at NaNoWriMo; 'Megalopolis' AI trailer snafu

News

• Short series app My Drama takes on Character.AI with its new AI companions (TechCrunch)

• Generative AI backlash hits annual writing event, prompting resignations (Ars Technica)

• ‘Megalopolis’ Finds a Fall Guy for AI Trailer Snafu and Hollywood Cries Foul (Hollywood Reporter)

Software

• Which AI video generator is the best? (Curious Refuge)

• Fine-tune FLUX.1 to create images of yourself (Replicate blog)

• Latent Navigation Exploring CLIP text space with FLUX.1 schnell (HuggingFace)

• Groq is hosting LLaVA-v1.5-7B which supports vision/image inputs and in our initial benchmarking response times were >4X faster than GPT-4o on OpenAI (X)

• Stability AI in Amazon Bedrock (Amazon)

• Texify is an OCR model that converts images or pdfs containing math into markdown and LaTeX that can be rendered by MathJax ($$ and $ are delimiters). It can run on CPU, GPU, or MPS (GitHub)

Research

• Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency (project page)

• Generating Consistent Long Depth Sequences for Open-world Videos (project page)

• ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis (project page)

• VideoLLaMB: Long-Context Video Understanding with Recurrent Memory Bridges (project page)

• Can Visual Foundation Models Achieve Long-term Point Tracking? (project page)

• Video Game Generation: A Practical Study using Mario (project page)

• Accurate Compression of Text-to-Image Diffusion Models via Vector Quantization (project page)

• FLUX that Plays Music (arXiv)

• PRoGS: Progressive Rendering of Gaussian Splats (arXiv)