In this episode of Emergent Behavior, @8teapi talks with Hedra co-founder Michael Lingelbach. Listen as he shares his vision for a future of AI-powered storytelling, where creators can seamlessly blend real and generated content to bring their unique visions to life. Hedra believes that AI can empower storytellers of all levels, enabling them to create professional-quality video content without needing extensive technical expertise.
Explore the democratization of video production with accessible AI tools and discover Hedra's vision for an AI-powered future where anyone can create compelling video content.
🔥 Apply to join over 400 founders and Execs in the Turpentine Network: https://hmplogxqz0y.typeform.com/to/JCkphVqj
--
RECOMMENDED PODCASTS:
🎙️ This Won't Last - Eavesdrop on Keith Rabois, Kevin Ryan, Logan Bartlett, and Zach Weinberg's monthly backchannel. They unpack their hottest takes on the future of tech, business, venture, investing, and politics.
Apple Podcasts: https://podcasts.apple.com/us/podcast/id1765665937
Spotify: https://open.spotify.com/show/2HwSNeVLL1MXy0RjFPyOSz
YouTube: https://www.youtube.com/@ThisWontLastpodcast
--
FOLLOW ON X:
@8teAPi (Ate)
@mjlbach (Michael)
@TurpentineMedia
--
LINKS:
Michael Lingelbach:
https://mlingelbach.com/
Hedra:
https://www.hedra.com/
--
TIMESTAMPS:
(00:00) Introduction
(02:29) Hedra: A Multimodal Foundation Model
(03:45) Diffusion Models and Controllability
(05:49) Audio as a Control Signal
(07:58) Talking Head Features and Performance
(11:41) Democratizing Storytelling
(14:13) Background and Inspiration
(17:17) Character One: First Release
(19:07) Technology and Development
(27:54) Challenges and Future Directions
(38:00) Model Scaling and User Feedback
(41:01) Technical Details and Uncanny Valley
(49:00) Social Media and Collaboration
(54:00) Multi-view Input and the Future
(57:21) Conclusion
Information
- Show
- Channel
- FrequencyUpdated Weekly
- PublishedJune 20, 2024 at 7:00 AM UTC
- Length58 min