Using VLMs for Video QA and Auto-Regenerating with Kling

KarlMuth · x · 2026-07-07

The author shared their video generation workflow: using MoviePy to inspect generated results frame-by-frame and a VLM to evaluate visual quality. Upon detecting subpar segments, it automatically triggers the Kling video model to regenerate them, adjusting prompts based on the VLM's feedback. To boost generation quality, they also built a reference image library (e.g., Boston dragon, dragon taking off, dragon flying) to aid in prompt construction.

Related event: Developers Share Automated AI Video Generation Workflows(3 posts)→

Original post →

More from Multimodal

Multimodal channel →