One prompt per monster: indie game bestiary built with GPT 2.5 art and Meshy text-to-motion
techhalla · x · 2026-10-15
techhalla shows his game bestiary workflow: 11 creatures from Cantabrian folklore, each generated with a single GPT 2.5 prompt into a medieval-miniature transparent PNG (via Magnific), with the page itself built by code so new creatures slot right in. Animations come from Meshy text-to-motion — one sentence like "wading through waist-deep river water, knees high" yields the clip; 10 AI clips plus 53 from a mocap library. Combats and dungeons are next.
Related event: Meshy launches text-to-motion for one-person game creation(2 posts)→
More from Multimodal
- Building Da Vinci's Inventions in 3D with Gemini Argon, No Blender Needed — DeryaTR_ · 2026-10-15
- AI Twitter Hypes Gemini Argon's 3D, One User Just Makes an Owl iPhone Sticker — _FelixSimon_ · 2026-10-15
- Runway integrates with Claude Motion to turn explainers into videos — tlakomy · 2026-10-15
- Scale CEO spotlights Muse Wonder: untrained for 3D yet beats Gemini 4 in physics visualization tests — alexandr_wang · 2026-10-15
- From a single image to a fully rigged, procedurally animated character — shekitup · 2026-10-15
- Seedance 2.5's Creative Upscale lets you reroll drafts at 480p, upscale only the keeper to 4K — anthara_ai · 2026-10-15