AI filmmakers say they finally control camera and blocking with new video models
jordanbayne · x · 2026-10-15
AI filmmaker UncannyHarry says that for the first time he feels true control over camera and blocking: output isn't a perfect 1:1 of the animatic, but follows it remarkably well — even leaving room for "actors" to contribute, like the tie-dye guy not walking away, which still works in the final cut. jordanbayne chimed in to praise the shot. The thread suggests AI video tools now support director-level storyboard control rather than pure prompt roulette.
Related event: AI Filmmaker Says New Workflow Finally Puts Him in Control of the Camera(3 posts)→
More from Multimodal
- Kling 4.0 now fully available, showcased with 'King Card' short film — DavidmComfort · 2026-10-15
- Krea 3 image editing beta opens: 2k edits in under 8s, claims Nano Banana Pro-level quality — TitusTeatus · 2026-10-15
- Diffusers adds full Flux.3 Image Klein support: FP8/NVFP4 quantized inference and bbox layout control — RisingSayak · 2026-10-15
- xiaohu demos video model across styles with in-video text rendering — xiaohu · 2026-10-15
- Midjourney Style Code sref 2898442999 Yields Consistent Claymation-Style Anthropomorphic Animals — sergeantsref · 2026-10-15
- Kling 4.0 lip-sync demo handles even fast-paced rap — xiaohu · 2026-10-15