Ice Queen and Dog Transform into Dragon in Snowstorm
A 15-second fantasy sequence where a woman and her black dog fall through a blizzard, find a glowing amulet, and transform into an Ice Queen and a giant ice dragon. The prompt uses shot-by-shot timecodes to stage the fall, transformation, and final flight over a kneeling walker army.
Shami @ShamiWeb3
Prompt (original, unmodified)
0–3s: Dark frozen sky, violent snowstorm, camera rushing downward, atmosphere inspired by Game of Thrones. A woman falls from the sky while tightly holding her dog — a black dog with a white chest and white paws, sharp ears, powerful intense stare. She screams loudly, “Aaaaah!” as they fall through the storm. She wears black leather northern warrior clothing: fitted leather corset, belts, long gloves, high boots, heavy fur cloak on her shoulders. 3–6s: They crash into a snowy valley. The woman rises to one knee and grabs a glowing ancient blue amulet. She looks at her dog and says: “Let’s do this.” The black dog with white markings growls and stares forward. In the distance, icy walkers appear through the blizzard. 6–9s: The amulet explodes with bright blue light. Ice spreads across the woman’s hands and face. Her leather clothing transforms into majestic black steel and ice armor with sharp detailed patterns. 9–12s: The woman fully transforms into the Ice Queen of the walkers — pale blue skin, glowing blue eyes, frozen crown, powerful dark armor. The dog begins transforming into a giant ice dragon, keeping its black fur and white chest markings. 12–15s: A massive black ice dragon with white markings and glowing blue eyes spreads its wings. The Ice Queen climbs onto its back and they rise into the storm, while the army of walkers kneels before them.
Reproduced verbatim from the original post. Never edited or translated. Everything outside this block is our own commentary.
How this prompt compares
The techniques this prompt uses are more common in fantasy prompts than in the library overall:
| Technique | In fantasy | Library average | Lift |
|---|---|---|---|
| aerial/drone | 15% | 11% | 1.44x |
| push-in | 17% | 12% | 1.4x |
| wide shot | 34% | 26% | 1.3x |
| volumetric | 51% | 23% | 2.23x |
Across all 5,926 prompts, the techniques used here appear at: wide shot 26%, volumetric 23%, low-key 17%, push-in 12%.
The 15s duration is not arbitrary: 71% of the prompts in this library that state a duration ask for exactly 15 seconds — Seedance 2.0 accepts clips up to 15 seconds, so 15s is the model's ceiling and the most common choice.
