A 30-Second Short Film Generated From a Single Prompt and a Few Image References
umesh_ai · x · 2026-09-28
Creator umeshai shared a 30-second short film generated with just a single prompt plus a few image references, and posted the exact prompt used.
The demo highlights how far video generation models have come on shot coherence and style control: no elaborate multi-step workflow, just reference images to anchor the visual style. The included prompt is a useful reference for creators experimenting with AI video.
More from Multimodal
- Viral Prompt Share: Stitched Stop-Motion World of Felt and Fabric — azed_ai · 2026-09-28
- Blogger slams MiniMax H3 portraits for oily skin and creepy 'zombie face' output — huangyun_122 · 2026-09-28
- One Midjourney --sref code nails 1970s Kodak disco style, full params shared — michaelrabone · 2026-09-28
- Two prompts: Claude Opus 5.5 codes, renders and self-checks a full 1080p promo video — sujingshen · 2026-09-28
- StepFun and ACE Studio launch StepAudio 3 Music, a foundation model for song generation — CodeByPoonam · 2026-09-28
- ComfyUI question: can premade Blender depth maps skip the ControlNet preprocessor? — DiddlyDinq · 2026-09-28