雨中咖啡馆肖像（图生视频）
She lowers her cup to the saucer, gazing out at the rain. Lightning cracks outside, illuminating the wet street for an instant — she turns toward the camera with a faint smile. Rain intensifies on the glass, streaks racing down, neon reflections rippling on the cobblestones. Slow dolly in toward her
A storyboard image gives Seedance visual anchors for character consistency, camera order, sound cues, and long-video handoff.
Keep the same visual style, lighting, subject identity, and camera rhythm across every connected 10-second block.
Use the same object, location, color palette, camera language, and sound direction as the global reference.
What the prompt tells Seedance to do
Use the storyboard as five connected motion beats.
Download every visual reference
Use each visible storyboard sheet with the matching copied Seedance prompt. Multi-block cases show every available sheet; older single-poster cases show the full public reference.
Why paid storyboard packs are different
Text-only video prompts often drift after 15 seconds. Cineprompt uses ChatGPT Image 2 / gpt-image-2 storyboard images as visual continuity anchors: one global story, one character reference, and one clean storyboard sheet per 10-second Seedance 2.0 block. That is the paid value: longer AI videos with consistent characters, locations, sound direction, and story handoffs.