Today in Generative Media
Vimeo adds GenAI tools; Rift is a local VSCode copilot; gpt-author writes novels
Vimeo Adds Generative AI Video Tools (voicebot.ai)
Morph releases Rift, an open-source AI-native language server and VSCode extension for local copilots. (Twitter) Code on GitHub.
gpt-author utilizes a chain of GPT-4 and Stable Diffusion API calls to generate an original fantasy novel. (GitHub) A 15-chapter novel can cost as little as $4 to produce, and is written in just a few minutes. The output is an EPUB file that can be uploaded directly to the Kindle store, including cover art. Prepare for a flood of content. (Ethan Mollick, Twitter)
You can now clone your voice using a few seconds of audio, give the robot personality, and deploy a clone of yourself. (Twitter) Powered by myshell.ai.
Meta-Personalizing Vision-Language Models to Find Named Instances in Video (CVPR 2023, project page)
MotionGPT: Finetuned LLMs are General-Purpose Motion Generators (arXiv)
RepoFusion: Training Code Models to Understand Your Repository (arXiv)
Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision (project page)