Recreating the Same Halloween Video One Year Later: From 5 Hours to a Few Steps
miilesus · x · 2026-11-01
Creator miilesus remade last year's Halloween video to show how far AI video generation has come.
2025 workflow (5 hours): LLM analyzed video frame by frame because VLMs weren't good enough; images generated per scene; separate motion prompts per scene; 5-second clips stitched together due to the 10-second generation limit.
2026 workflow (a few steps): LLM analyzed the full video directly; only 2 clips generated (30s + 20s); stitched and done.
"Less soul, more speed," the author quips.
More from Multimodal
- VFX Supervisor Open-Sources 20 Skills for Building an Automated Motion Design Pipeline with Claude Opus 5.5 — GCWebDesigner · 2026-11-01
- Open-H3-Regenerate-2K tested: sharper faces but up to 2x generation time — gutster_95 · 2026-11-01
- AI-made Halloween special drops with action, jokes and horror easter eggs in 4K — charis_ai · 2026-11-01
- AI filmmakers are making movies Hollywood never would, on minimal budgets — DavidmComfort · 2026-11-01
- IronLeo78 MTV: a two-node ComfyUI pack that turns any song into a music video — IronLeo78x · 2026-11-01
- CoBit paper: one continuous bitstream diffusion recipe spans language, image, speech and protein generation — LucaAmb · 2026-11-01