Video generation with realistic motion

Practical AI: Machine Learning, Data Science, LLM

We seem to be experiencing a surge of video generation tools, models, and applications. However, video generation models generally struggle with some basic physics, like realistic walking motion. This leaves some generated videos lacking true motion with disappointing, simplistic panning camera views. Genmo is focused on the motion side of video generation and has released some of the best open models. Paras joins us to discuss video generation and their journey at Genmo.

Join the discussion

Changelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!

Sponsors:

• Domo – The AI and data products platform. Strengthen your entire data journey with Domo’s AI and data products.

Featuring:

• Paras Jain – LinkedIn, X
• Chris Benson – Website, GitHub, LinkedIn, X
• Daniel Whitenack – Website, GitHub, X

Show Notes:

• Genmo

Something missing or broken? PRs welcome!

Разделы

1. Welcome to Practical AI (00:00:00)

2. Paras Jain (00:00:45)

3. To be a video model builder (00:04:26)

4. Curation (00:06:46)

5. Harder things to get right (00:09:00)

6. Sponsor: Domo (00:14:37)

https://ai.domo.com

7. Team snapshot (00:15:59)

8. The evolution (00:19:07)

9. Model size (00:22:36)

10. Is compression inevitable? (00:28:24)

11. Mochi (00:30:09)

12. How people use the model (00:33:24)

13. Editing (00:34:51)

14. Video gen in 2025 (00:36:01)

15. What is creativity? (00:40:06)

16. What's your vision? (00:42:03)

17. Outro (00:43:47)