
Reference Images:
{ "task": "Create a realistic iPhone-style photobooth collage (4 photos in a 2x2 grid)", "subjects": [ { "id": "Subject 1", "description": "EXACTLY the same as in the Reference Image (same face, hairstyle, skin tone, body proportions, overall appearance).", "outfit": "EXACTLY the same as in the Reference Image. Do not change clothing, glasses, or accessories." }, { "id": "Subject 2", "description": "EXACTLY the same as in the Reference Image (same face, hairstyle, skin tone, body proportions, overall appearance).", "outfit": "EXACTLY the same as in the Reference Image. Do not change clothing, glasses, or accessories." } ], "scene": { "location": "Inside a small BOX-style photobooth", "background": "Matte blue walls and floor, tight and clean corner", "camera_look": "Ultra-wide angle / slight fisheye distortion typical of photobooth cameras. iPhone 17 Pro, wide-angle.", "lighting": "Bright neutral white flash, even lighting, soft shadows, realistic skin texture. No warm tones.", "aesthetic": "4K, amateur photobooth style, high natural contrast, no filters, no blur, no text, no watermark." }, "layout": { "type": "2x2 collage", "aspect_ratio": "9:16", "style": "No borders, no lines, no separators. Each photo fully fills its quadrant." }, "frames": [ { "position": "top-left", "content": "Subject 1 leaning diagonally toward the camera from the left, arm down, serious-playful expression. Subject 2 behind in the center, arms raised in a 'strongman' pose, smiling." }, { "position": "top-right", "content": "Subject 2 leaning toward the camera with hands on knees, curious expression. Subject 1 enters very close from the right, head tilted and arm arched forming half a heart, soft smile." }, { "position": "bottom-left", "content": "Piggyback: Subject 1 on Subject 2’s back, arms around the shoulders. Both laughing, faces very close to the camera, dynamic feeling." }, { "position": "bottom-right", "content": "Subject 2 leaning to one side making a funny face. Subject 1 behind making 'claw/horn' gestures over their head, with a slight playful pout." } ] }

Museum exhibit. Dinosaur skeletons, spotlights, glass cases.

Generate a hyper-realistic, live-action movie still of a martial artist character inspired by fighting games. The character stands in a gritty, damp urban alleyway at night. They have visible battle scars, sweat dripping down their face, and textured, worn clothing. The lighting should be atmospheric, derived from streetlamps and neon signs, creating a moody, noir-like aesthetic. The render must look indistinguishable from a high-budget film production, avoiding any cartoonish proportions.

A collectible toy figure of a white bunny in a vintage copper diving suit. The helmet faceplate is a glass bubble showing the bunny's face. The suit has tiny barnacles attached. Finish: Metallic copper paint with slight weathering. Standing on a small coral base.

Photorealistic cinematic portrait of a stylish young adult woman, travel influencer glamour aesthetic, medium shot, eye-level camera angle, 3:4 aspect ratio. Subject in elegant fashionable outfit (user-defined color and style), well-groomed appearance, soft glam makeup, natural skin texture, expressive eyes, confident yet dreamy expression. Pose: (choose one – seated on ledge / standing confidently / walking naturally / leaning casually / hair-touch pose / editorial fashion pose). Body language looks natural and relaxed, influencer-style composition. Location: (insert famous landmark / city / travel destination). Foreground includes realistic environmental elements the subject interacts with. Background softly blurred with cinematic depth of field. Lighting: cinematic mixed lighting setup – warm key light on face and hair, ambient fill light from environment, practical or architectural lights in background creating depth and atmosphere. Time of day: (golden hour / blue hour / night / sunrise). Mood: cinematic, luxurious, romantic, atmospheric, travel editorial. Camera & render: high-end DSLR or mirrorless camera, portrait prime lens (50mm or 85mm), shallow depth of field (f/2.0–f/2.8), sharp focus on subject, realistic shadows and highlights. Post-processing: ultra-realistic textures, subtle 35mm film grain, natural color grading, high dynamic range, professional photography look, 8K ultra-HD quality. No text, no watermark, no logos, clean composition, social-media ready, premium aesthetic.

Create an illustration of a city park using Gouache paint. Gouache is opaque and matte, drying to a flat, velvety finish. The colors should be vibrant and solid, without the transparency of watercolor. The scene features people relaxing on green grass under stylized trees. The visual style is charming and illustrative, like a mid-century travel poster.

Create 3D isometric miniature of "Paris." 45-degree view. Eiffel Tower, Seine. "Claymorphism" texture (matte). Pastel background.

{ "template_id": "white_crochet_monokini_santorini_v1", "version": "1.0.0", "goal": "Recreate the reference photo EXACTLY — pose, camera angle, lighting, background, monokini design — while replacing ONLY the woman's identity with the uploaded subject. No other creative changes allowed.", "identity": "save as reference photo", "pose_anchor": { "head": { "tilt_direction": "backwards", "tilt_angle_degrees": 25, "gaze": "eyes open, looking up at sky" }, "torso": { "posture": "lying back on pool edge, elbows supporting" }, "arms_hands": { "both_hands": "behind head, fingers interlaced" } }, "outfit_lock": { "type": "white crochet monokini", "details": "high-cut legs, deep V front, open crochet pattern, thin straps" }, "environment_lock": { "location_type": "private cave pool in Oia, Santorini", "background": [ "whitewashed walls", "caldera view", "bright Aegean blue sea and sky" ] }, "lighting_color": { "time_of_day": "midday", "color_temperature": "5600K" } }

{ "project_name": "Auto_Creative_Music_Video_Storyboard_Generator", "version": "4.0 (Video Clip Focus - Multi-Input)", "ai_role": "You are a visionary Creative Director and Cinematographer for a high-end music video. Your goal is to create a cohesive, visually stunning 9-scene storyboard based on provided visual references.", "input_configuration": { "source_material": "Multiple Uploaded Images. The AI must synthesize all provided images to establish the definitive subject(s), color palette, lighting scheme, and overall aesthetic.", "video_clip_style_selector": { "description": "Select the overarching genre/mood for the music video clip behavior.", "options": [ "Creative", "Surreal", "Absurd", "Dreamlike", "High-Fashion", "Cyberpunk", "Gothic", "Abstract" ], "selected_style": "Clay motion" } }, "processing_rules": { "consistency_is_paramount": "Strictly maintain the visual identity established by the input images across all 9 scenes. The subject's features, the specific lighting mood (e.g., neon stripes, iridescence), and the environment style must never deviate.", "apply_selected_style": "Inject the mood and behaviors of the 'selected_style' into the movement, composition, and events of the scenes. (e.g., if 'Surreal', gravity might behave oddly; if 'Absurd', actions might be illogical).", "imply_motion": "These are not static photos. Each panel must look like a still frame taken from a moving video clip, implying action, camera movement, or atmospheric shifting.", "no_text_overlays": true, "output_aspect_ratio": "16:9 for all panels." }, "scene_progression_structure": { "note": "Design 9 distinct visual beats representing the flow of a music video.", "row_1_introduction": { "panel_1": "Opening Scene: Establishing the mood and environment. Subtle introduction of the subject.", "panel_2": "Focus on Detail: A close cinematic shot emphasizing a key textural element from the input (e.g., makeup, clothing material, light reflection).", "panel_3": "Building Atmosphere: The subject interacts with the environment in a way defined by the selected style." }, "row_2_escalation": { "panel_4": "Dynamic Action: The energy increases. Stronger movement or a shift in lighting intensity.", "panel_5": "The 'Surreal' Turn: A moment that heavily highlights the selected video style (e.g., an impossible angle, abstract background shift, unusual pose).", "panel_6": "Intense Emotion: A powerful, emotive shot focusing on the subject's connection to the (implied) song." }, "row_3_climax_and_resolution": { "panel_7": "Visual Climax: The most visually striking and complex shot. The peak of the video's energy.", "panel_8": "Pulling Back: A wider view showing the aftermath of the climax or a change in state.", "panel_9": "Closing Scene: A resolving shot that fades out or ends the visual journey, leaving a lasting impression." } }, "final_prompt_instruction": "Synthesize all uploaded input images into a single, cohesive visual identity. Acting as a Creative Director, generate a 3x3 grid storyboard composed of 9 high-quality video stills. You must strictly apply the requested 'selected_style' to the narrative flow defined in the 'scene_progression_structure'. Ensure every panel looks like a frame from the same high-budget music video, maintaining perfect consistency in subject and lighting. Do NOT include any text overlays on the final images." }