ZHFantasy Warrior Raises Glowing Sword in Ancient Ruins
An image-to-video prompt that turns a reference character into a cinematic fantasy warrior standing in ancient mountain ruins. It specifies an ultra-realistic face, glowing magical sword, and an epic 15-second story arc of darkness and heroism. The technique relies on a reference image for face consistency plus cinematic close-up framing with shallow depth of field.
Zyrella @Zyrellix
Prompt (original, unmodified)
[Character] A brave and powerful female warrior with long braided hair, sharp glowing eyes, and a fearless expression. She wears detailed fantasy armor and holds a glowing magical sword. Ultra realistic face, cinematic fantasy style, dramatic lighting, highly detailed textures, same face as reference image. [Place] Ancient fantasy kingdom ruins surrounded by giant mountains, broken stone castles, glowing fire torches, mystical fog, magical atmosphere, cinematic sunset lighting, epic battlefield environment, ultra detailed fantasy world, realistic 4K scenery. [Camera] Cinematic close-up shot with shallow depth of field, soft background blur, ultra realistic lens effect, movie-style composition, sharp focus on the warrior’s face, 85mm cinematic lens, dramatic shadows, high detail, 4K quality. [Story – 15 Seconds] A mysterious warrior girl with magical powers discovers an ancient hidden secret inside ruined kingdoms. As eternal darkness spreads across the land, she raises her glowing magical sword and begins a dangerous journey to protect the weak and save the world. Epic cinematic action, emotional intensity, powerful fantasy atmosphere, fast-paced storytelling, dramatic ending shot. [Rule] A true warrior protects the weak, even when the whole world stands against her.
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 |
|---|---|---|---|
| volumetric | 51% | 23% | 2.23x |
Across all 5,926 prompts, the techniques used here appear at: close-up 40%, volumetric 23%, golden hour 17%.
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.
