AI filmmaking workflow: Midjourney start frame + Blender camera + Seedance video
TinfoilTricorn · x · 2026-10-12
A viral hands-on demo of an AI filmmaking workflow: generate a start frame in Midjourney, match character poses and animate the camera in Blender, then feed both into ByteDance's Seedance video model.
The author didn't expect it to work, but the result kept two characters consistent, delivered solid performances, and the camera move tracked perfectly through the entire shot—even the soup in the scene looks great. A notable multi-tool pipeline for precise camera control, multiple characters, and dialogue in AI video creation.
More from Multimodal
- Procedural MetaHumans in three.js With an Easy Skinning Approach — jasonkneen · 2026-10-13
- Long Shot Studio 0.8.2 adds 64-shot chaining and auto ComfyUI crash recovery — R34vspec · 2026-10-13
- Surreal AI image series "Sometimes, we need fire" goes viral — gizakdag · 2026-10-13
- Antonio Banderas to star in AI-powered feature 'Cortés' from Utopai Studios, now shooting in Paris — lmoroney · 2026-10-13
- Minimax H3 Refmod workflow: character-consistent video from photos plus a voice sample, no LoRA training — AlsterwasserHH · 2026-10-13
- An indie game ad made entirely with Google Flow and Suno — ahmettnq · 2026-10-13