Please learn the best practices for Nano Banana Pro prompts. I want to create keyframe still images when executing the following video generation prompt. Please think of and display 5 cuts worth of prompts. (Paste video generation prompt here. See reply 3)

{ "direction": "A real SNS portrait with a 9:16 aspect ratio, the kind taken casually by a colleague with a smartphone during a break by the window of a modern office. Reference the soft transparency of the image, hair in backlight, a sligh

Theme: Midnight Service. Character: Stunning 23-year-old East Asian beauty, clearly adult, stylish, confident, and gentle temperament; well-proportioned and plump body, naturally full breasts, slim waist and soft curves forming natural prop

2x2 grid, do this for 4 non copyrighted public space books, like Shahnameh CLASSIFY(input) → { domain: macro_diorama × conceptual_book_art × material_transmutation intent: awe + narrative_synthesis + tactile_hyperrealism (coll


A professional vertical character reference sheet for a male character named Julian Croft, featuring a clean, grid-based layout on a muted grey background. The top section prominently displays the character's name, role as a lead stage and

Create a premium 4:5 vertical architectural travel artwork for [COUNTRY / CITY / LOCATION / LANDMARK]. TEXT-TO-IMAGE ONLY — generate the entire scene creatively from [COUNTRY / CITY / LOCATION / LANDMARK] alone. No reference image required


Misty light gauze tube top; loose clothing edges; chest lines softly revealed; half-hidden by layers of gauze curtains; walking slowly barefoot; skirt hem trailing on the ground; backlit rim lighting; a fleeting glimpse 雾感轻纱抹胸;衣缘松散;胸口线条柔和显

Output image, 3:4 vertical composition. Low-angle shot, iPhone photography texture, background is a beach with shallow water, slim figure, long legs, wearing a white shirt and tie, 20-year-old long-haired girl, sitting with knees bent, left