Creator makes full AI video with Seedance 2.5 using plain prompts, only two generations
LudovicCreator · x · 2026-09-19
Creator @jamesyeung18 shared a short film made entirely with Seedance 2.5 (Dreamina), prompted in plain language with no ChatGPT or other tooling assistance — just 3 Midjourney images as references. The output matched about 90% of his vision on only two generation attempts, though he admits the result is far from perfect.
More from Multimodal
- Experimental video mixes visual styles, generated with Seedance 2.5 on Adobe Firefly — umesh_ai · 2026-11-04
- Hailuo AI claims H3 scored perfect on language tests; Japanese creator praises its Japanese signage fidelity — Hailuo_AI · 2026-11-04
- YANAMI: 400K-dialog multimodal dataset shows models still fail at stateful multiturn interaction — Shengyu Wang · 2026-11-04
- Open-source Idol model turns a single image into 3D in 45s on 8GB VRAM — Promptmethus · 2026-11-04
- ComfyUI v0.44.0 released with new Patina texture nodes — Fcking_Chuck · 2026-11-04
- Krea 3 technical report released: a deep dive into data, architecture and training — bdsqlsz · 2026-11-04