Creator shares full workflow for a 30-second AI necromancer animation built with LUMA
LudovicCreator · x · 2026-09-07
LudovicCreator details the end-to-end workflow behind a 30-second necromancer summoning animation made entirely in LUMA, no footage used:
- Ideation: started from a vibe (necromancer, wraith forming from green smoke, moonlit graveyard), with toxic-green witchfire as the only light source.
- Five-model bake-off: the same brief run through Nano Banana Pro, Seedream 4.0, Uni-1.1, GPT Image 2, and Seedream 5.0 Pro; the Seedream 5.0 Pro concept won on silhouette, robes, and hood shadow.
- Character locking: two custom skills — one produced a character reference pack (Nano Banana Pro) plus a front/back/side/portrait turnaround sheet (GPT Image 2), with an identity-consistency check before animating.
- Animation: a second custom skill drove Seedance 2.5 through one continuous 30-second crescendo (graveyard wide shot → rising witchfire → wraith reveal), with native synced audio (drone, incantation, wind, spectral shriek).
Notably, outputs from different image models stayed highly consistent — including the same six-fingered right hand.
Related event: Creator Builds 30-Second Necromancer Animation Entirely with LUMA AI(2 posts)→
More from Multimodal
- Two Midjourney sref codes for grainy pastel fashion illustration style — sergeantsref · 2026-10-23
- Three free ways to try MOSS-Image: API playground, HF Space, ComfyUI — songguoxiansen · 2026-10-23
- Open-source MOSS-Image tops 1M ComfyUI downloads, 5B model rivals closed rivals — songguoxiansen · 2026-10-23
- GAFU Uses Generation-Side Representations to Boost Fine-Grained Visual Understanding in Unified Multimodal Models — Tengju Ru · 2026-10-23
- MiniMax Design MCP goes live: create with Design inside Codex and other agents — Hailuo_AI · 2026-10-23
- Quiver's detailed SVG generation sparks debate: code-drawn images could replace pixel-based image models — stuffyokodraws · 2026-10-23