Kling 3.0's 15-second cinematic fantasy clip surprises with character consistency
eyishazyer · x · 2026-09-14
The author used Kling 3.0, Kuaishou's video model, to generate a 15-second high-budget-looking dark fantasy sequence: a lone torch-carrying traveler inside a vast underground cavern.
He shared the full prompt, with key techniques:
- Locking character appearance (hair, clothing, build, props) in detail and demanding full consistency across the sequence;
- Specifying environment and atmosphere (massive stone formations, mysterious carvings, thick mist) for cinematic quality.
His prior experience with AI video: shots stutter, lighting goes flat under camera movement, and the illusion drifts apart after a few seconds. Kling 3.0's character consistency and camera stability surprised him.
Related event: Kling 3.0 tested: stable camera moves and strong character consistency(2 posts)→
More from Multimodal
- Floor-plan-to-whitebox demo shows Astra hallucinating camera positions — letandrewcook · 2026-09-14
- 10 ChatGPT photo-editing prompt templates that beat vague one-line requests — TawohAwa · 2026-09-14
- Seedance 2.5 demo shows realistic skin pores and flyaway hairs in motion — nikola_mr64990 · 2026-09-14
- Dev open-sources Claude skills repo that turns LLM into a creative partner with a web studio UI — jh3yy · 2026-09-14
- AI-generated seaside coming-of-age scene looks straight out of a real film — SimplyAnnisa · 2026-09-14
- Midjourney V8.2 style code 612407510 earns community praise — azed_ai · 2026-09-14