Text to Image
Tarzan and Jane Cosplay Waterfall Triptych Prompt - Nano Banana Pro AI Prompt for Social Media Post — AI Image Prompt
A highly detailed, multi-panel JSON prompt for generating a cinematic, photorealistic triptych (three-panel image) depicting a live-action cosplay of Tarzan and Jane inside a lush jungle cave near a waterfall. The prompt specifies camera equipment (ARRI Alexa), lighting, and detailed emotional interactions between the characters, focusing on Tarzan examining Jane's white glove. - AIPinMaker
Prompt
{
"generation_request": {
"meta_data": {
"tool": "NanoBanana Pro",
"task_type": "photoreal_cinematic_cosplay_jungle_romance_triptych",
"version": "v1.0_TARZAN_JANE_COSPLAY_WATERFALL_GLOVE_TRIPTYCH_NO_TEXT_EN",
"priority": "highest",
"language": "en"
},
"references": {
"reference_image_style": {
"source": "UPLOAD_REFERENCE_IMAGE (OPTIONAL)",
"purpose": "POSE_COMPOSITION_EMOTION_ANCHOR",
"strict_lock": false,
"preserve_pose": true,
"preserve_composition": true,
"preserve_vibe": true
}
},
"output_settings": {
"aspect_ratio": "3:4",
"orientation": "portrait",
"resolution_target": "ultra_high_res",
"render_style": "cinematic_photoreal_film_still",
"sharpness": "crisp_but_natural",
"film_grain": "subtle_35mm",
"dynamic_range": "natural_not_hdr",
"color_grade": "cool_jungle_blues_green_shadows_warm_skin_tones",
"skin_rendering": "real_human_skin_texture_visible_pores",
"lens_and_camera": {
"camera": "ARRI_Alexa_Mini_LF",
"lens": "50mm_prime",
"aperture": "f1.8",
"focus_style": "shallow_depth_of_field_subject_priority"
},
"lighting": {
"key": "soft_diffused_waterfall_light",
"fill": "natural_jungle_bounce",
"rim": "cool_backlight_from_cave_opening",
"mood": "curious_intimate_emotional"
},
"background": {
"environment": "lush_jungle_cave_with_waterfall_vines_and_moss",
"atmosphere": "soft_mist_humidity_air_particles",
"bokeh": "gentle_background_blur"
}
},
"scene": {
"global_description": "A live-action photoreal cosplay interpretation of Tarzan and Jane inside a lush jungle cave near a waterfall. Jane is a young woman with fair skin, expressive eyes, and long brown hair worn loose. She wears a modest {argument name="jane dress color" default="yellow"} Victorian-inspired dress with structured bodice, long sleeves, and white gloves. Tarzan is a muscular athletic man with deep tan skin and long dark hair, shirtless, wearing a simple brown loincloth. The interaction is respectful, curious, and emotionally charged. No animation look, no exaggeration, fully realistic anatomy, fabric physics, and lighting.",
"shots": [
{
"shot_id": "PANEL_01",
"framing": "medium_shot",
"action": "Jane raises her gloved hand cautiously as Tarzan gently holds her wrist, examining the glove with curiosity. Jane looks surprised but not afraid. Tarzan’s posture is alert yet gentle.",
"expression": "curiosity_meets_uncertainty",
"micro_details": "realistic hand anatomy, glove fabric tension, subtle muscle flex, natural eye moisture, believable cave humidity"
},
{
"shot_id": "PANEL_02",
"framing": "medium_close_up",
"action": "Tarzan studies the white glove closely, lifting it sligh3fPrompt breakdown
- Subject
- Tarzan and Jane cosplay in lush jungle cave with waterfall, vines and moss; Jane in yellow Victorian dress with white gloves, Tarzan shirtless in brown loincloth examining her gloved hand
- Style
- photoreal_cinematic_cosplay_jungle_romance_triptych rendered as cinematic_photoreal_film_still with ARRI_Alexa_Mini_LF 50mm f1.8 and subtle 35mm film grain
- Lighting
- soft_diffused_waterfall_light key, natural_jungle_bounce fill, cool_backlight_from_cave_opening rim, cool_jungle_blues_green_shadows_warm_skin_tones color grade
- Composition
- portrait 3:4 triptych with medium_shot PANEL_01 showing Jane raising gloved hand and Tarzan holding her wrist, medium_close_up PANEL_02 of Tarzan studying the glove fabric, shallow depth of field subject priority
- Mood
- curious_intimate_emotional with respectful interaction, visible hand anatomy, glove tension and cave humidity
Remix ideas
- swap Jane dress color to deep emerald while keeping white gloves to shift Victorian explorer tone
- change lens to 35mm for wider framing that pulls more waterfall mist into the background bokeh
- add faint moss texture on Tarzan's shoulder and realistic water droplets on the glove for extra humidity detail
Reference images
How to use this AI Image prompt template
1Copy the prompt — grab this template’s prompt and negative prompt. 
2Pick a model — choose a recommended AI model for the best match. 
3Generate — open the studio with one click and create your result.
Related templates
Woman in a Geodesic Time Machine
Create a creative image of Woman In A Geodesic Time Machine. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: photography. Reference: woman-in-a-geodesic-time-machine-5194.
Unraveling Figure Effect Comparison
Create a creative image of Unraveling Figure Effect Comparison. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: photography. Reference: unraveling-figure-effect-comparison-13376.
Tang Dynasty makeup steps prompt
Create a creative image of Tang Dynasty Makeup Steps Prompt. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: photography. Reference: tang-dynasty-makeup-steps-prompt-15932.
Pearl and Diamond Empress
Create a creative image of Pearl And Diamond Empress. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: photography. Reference: pearl-and-diamond-empress-4142.
Gothic Lolita Furisode Outfit
Create a creative image of Gothic Lolita Furisode Outfit. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: photography. Reference: gothic-lolita-furisode-outfit-20834.
Surreal Cinematic Subway Studio
Cinematic 35mm photography of a young woman sitting backwards on a modern chrome chair inside an enormous underground subway station transformed into a surreal creative studio, uploaded face (reference image) used 100% as reference. She is wearing a dark graphite oversized shirt (top), loose white trousers (bottom), and white slip-on sandals. She has long, silky dark hair, flawless skin, elegant feminine features, and a confident, creative expression. Around her, the station walls are covered with layered poster collages, ripped magazine spreads, handwritten typography experiments, floating transparent UI windows, and glowing directional signs displaying phrases like “Design Is Everywhere,” “Create the Unexpected,” and “Stay Original.” Abandoned train tracks are filled with scattered sketchbooks, camera lenses, open laptops showing editing software, rolls of film, and oversized blueprint papers blowing dramatically through the station from incoming wind. Cinematic fluorescent lights flicker overhead while distant train headlights create atmospheric haze, volumetric lighting, and reflective highlights across the polished floor. Muted monochrome tones dominate the image, enhanced by faded cyan highlights and subtle warm orange accents from glowing neon signs. The composition feels like a luxury streetwear campaign fused with a futuristic graphic design exhibition, blending modern creative culture with urban industrial aesthetics. Highly detailed textures, cinematic depth, realistic skin texture, soft analog film grain, slightly desaturated editorial color grading, premium fashion photography, immersive environmental storytelling, ultra-sharp focus, masterpiece-quality detail, luxury Instagram campaign aesthetic, visually rich and emotionally cinematic composition.3a:T75d,Cine
Explore more prompts
Browse more AI image and video prompts by category.
FAQ
- Why does the prompt specify white gloves and fabric tension details?
- The white gloves become the central interaction point in both panels, with micro_details calling for realistic glove fabric tension and hand anatomy to ground the cosplay in photoreal physics.
- How is the triptych optimized for social media?
- The 3:4 portrait orientation, cinematic shallow depth of field, and emotionally charged two-character focus create scroll-stopping vertical content without text or animation artifacts.