A 3D blocking pass gives AI video frame-level control before Seedance 2.0 renders
andrew_n_carr · x · 2026-07-24
The post lays out a 3D-first workflow for directing AI video instead of relying on pure prompt lottery.
The team writes the character and scene first, builds four-view reference sheets, creates a 3D blocking pass in Maya/Blender/Unreal, and then feeds the motion reference plus visual references into Seedance 2.0 for neural rendering. The goal is frame-by-frame control over timing, camera, and spatial relationships before the video model does the final render.
More from Multimodal
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26
- LichtFeld Studio v0.5.4.3 ships community-built SteadySplats, POPSpa and Voxelization — janusch_patas · 2026-10-26
- One prompt to a 2-3 min narrated short: hands-on test of Antigravity video generation — AI_Andrew · 2026-10-26
- Creator makes 10,564-frame animated short entirely with Gemini toolchain — AI_Andrew · 2026-10-26
- FLUX.3 Klein step-distilled to 4-8 steps with CFG baked in — Fit-Structure-6489 · 2026-10-26
- ostris pre-training "Primal VAE": 1-channel latents match modern 8x VAEs via patching — ostrisai · 2026-10-26