AI 提示词库

{ "prompt": "Use the uploaded image as the primary reference for composition, proportions, pose, objects, and overall layout. Preserve the original identity and facial features accurately. Convert the image into a refined pencil and ink sketch illustration. Use clean hand-drawn line work, controlled cross-hatching, and soft shading to define form and depth. Keep facial features, eyes, and hands sharp and expressive while allowing background details to remain minimal and lightly sketched. Overall look should feel like a professional hand-drawn illustration—elegant, timeless, and artistic (not cartoon).", "negative_prompt": "identity change, face mismatch, cartoon, anime, messy scribbles, heavy black fills, low quality, blur, noise, distorted anatomy, extra limbs, text, watermark, logo", "style": "pencil and ink sketch illustration", "mood": "classic, artistic, calm", "lighting": "illustrative light shading", "texture": "paper grain, pencil strokes", "render_quality": "ultra high resolution, hand-drawn quality", "reference_strength": 0.9 }

{ "system_role": "NANO_BANANA_PRO_VISUALIZER", "mode": "MACRO_FOOD_HORROR", "subject_override": "An inflatable pool toy shaped like a T-Rex, but the material is raw, sweating salmon fillet flesh", "lighting_engine": { "type": "HARSH_DIRECT_FLASH", "exposure": "overexposed_highlights", "shadows": "pitch_black_hard_edge", "reflection": "wet_mucous_gloss" }, "camera_simulation": { "lens": "100mm_macro", "aperture": "f/22", "iso": "3200", "imperfections": ["chromatic_aberration", "sensor_dust", "grease_on_lens"] }, "composition": "centered, claustrophobic cropping, awkward scientific documentation angle" }

A {argument name="character type" default="[CHARACTER / FIGURE]"} entirely built from flowing {argument name="energy type" default="[ENERGY / LIGHT / COLORS]"}, as if captured in motion. Trails form limbs and features, glowing softly in {argument name="atmosphere" default="[ATMOSPHERE]"}, dramatic cinematic composition.

{ "image_generation_prompt": { "subject": { "description": "A tiny man sitting and leaning against a tall young bean sprout", "clothing": "Casual pink t-shirt and black shorts", "pose": "Sitting relaxed on the ground, resting under a giant plant stem" }, "environment": { "setting": "Surreal macro-fantasy scene, extreme close-up", "elements": "Detailed textures of soil, pebbles, roots, and young seedlings", "plant_details": "Bean sprout towering above with fresh green leaves, pale stems, and visible seed halves still attached" }, "technical_specs": { "style": "Macro photography, Hyper-realistic, Cinematic", "lighting": "Natural outdoor lighting, realistic shadows, vibrant colors", "camera_effects": "Shallow depth of field, soft blurred background (bokeh), crisp highly detailed foreground", "resolution": "8K, Ultra-detailed" }, "full_prompt_text": "A surreal macro-fantasy scene showing a tiny man wearing a {argument name=\"shirt color\" default=\"pink t-shirt\"} and black shorts, sitting and leaning against a tall young bean sprout. The environment is captured in extreme close-up macro style, revealing detailed textures of soil, pebbles, roots, and young seedlings. The bean sprout towers above him with fresh green leaves, pale stems, and visible seed halves. Shallow depth of field with soft blurred background, crisp foreground. Natural outdoor lighting, realistic shadows, vibrant colors, whimsical scale difference, hyper-realistic clarity." } }

**"photography, transparent vertical glass filter.** **A humanoid silhouette wearing a casual, minimal {argument name="shirt color" default="light-colored T-shirt"},** **photography, transparent vertical glass filter that creates refracted,** **sliced distortions across his body.** **The distortions create a layered, fragmented visual effect.** **The silhouette is blurred and vague due to the glass, chaos 10** **--ar 4:5 --raw --profile pz8hopv --stylize 220"**

{ "prompt": "A hyper-realistic adult woman as a marionette (puppet), lifelike human skin pores and micro-details, realistic facial anatomy, natural hair strands, subtle makeup, melancholic expression, suspended and controlled by thin silk strings attached to wrists, shoulders, and head. Post-modern surreal environment: fragmented concrete walls, floating geometric shapes, minimalist art installation vibe, soft haze and volumetric light. Subtle marionette cues: barely visible seam lines at elbows and knees, tiny joint mechanics hidden under skin-like material, faint porcelain crack textures blending into realistic skin (very subtle). Dramatic top light emphasizing strings, strong contrast shadows, cinematic depth of field, 50mm lens look, photorealistic textures, ultra-detailed, 8K, high realism, tasteful post-modern color grading.", "negative_prompt": "cartoon, anime, illustration, lowres, blurry, deformed, extra limbs, extra fingers, bad hands, bad anatomy, plastic doll face, uncanny overly smooth skin, overexposed, text, watermark, logo, signature, jpeg artifacts, noisy, grainy", "size": "1080x1920", "aspect_ratio": "9:16", "style": { "render": "photorealistic", "mood": "melancholic_cinematic", "art_direction": "post_modern_installation" }, "camera": { "shot_type": "medium_full_shot", "angle": "slight_low_angle", "lens_mm": 50, "aperture": "f/1.8", "focus": "face_and_strings", "depth_of_field": "shallow" }, "lighting": { "key_light": "top_spotlight", "fill_light": "soft_bounce_low", "rim_light": "subtle_back_rim", "effects": ["volumetric_light", "soft_fog"] }, "environment": { "location": "post_modern_gallery_space", "materials": ["raw_concrete", "matte_plaster", "metal_frames"], "elements": ["floating_geometric_forms", "fragmented_wall_panels", "minimalist_installation_platform"] }, "subject": { "type": "adult_woman", "realism_level": "high", "pose": "standing_suspended", "emotion": "melancholic_distant", "wardrobe": "{argument name=\"wardrobe style\" default=\"minimalist_avant_garde_outfit_muted_tones\"}" }, "details": { "strings": { "material": "thin_silk", "visibility": "clearly_visible", "attachment_points": ["wrists", "shoulders", "head"] }, "marionette_traits": { "seams": "subtle", "joint_cues": "minimal", "cracks": "very_subtle_porcelain_like" }, "texture_quality": "ultra_detailed_microtextures" }, "quality": { "resolution": "8k", "sharpness": "high", "color_grade": "cinematic_post_modern" } }

Do this for a {argument name="painting type" default="random famous Asian painting"} <instruction> Input A is a Famous Painting (e.g., The Mona Lisa, The Scream). Analyze: The brushstroke technique, the 3D depth implied, and the hidden symbols. Goal: A "Paint Tube Squeeze." A giant, realistic oil paint tube sitting on a palette. Rules: Action: The tube is being squeezed, and the paint coming out is not just a blob, but it forms the 3D landscape of the painting. The Mona Lisa's face is emerging in 3D relief from the 2D smear of paint. Texture: Viscous, thick oil paint texture (impasto). Props: Paintbrushes, a dirty rag, a palette knife, plus culture appropriate tools and environment. Lighting: North-light studio lighting, true color representation. Output: ONE image, 4:5, "artistic process" aesthetic. </instruction>

Do this for {argument name="painting name" default="Starry Night"}<instruction> Input A is a Famous Painting (e.g., The Mona Lisa, The Scream). Analyze: The brushstroke technique, the 3D depth implied, and the hidden symbols. Goal: A "Paint Tube Squeeze." A giant, realistic oil paint tube sitting on a palette. Rules: Action: The tube is being squeezed, and the paint coming out is not just a blob, but it forms the 3D landscape of the painting. The Mona Lisa's face is emerging in 3D relief from the 2D smear of paint. Texture: Viscous, thick oil paint texture (impasto). Props: Paintbrushes, a dirty rag, a palette knife, plus culture appropriate tools and environment and tiny 3D printed version of the painter on the desk drawing it on a tiny easel and a newspaper headline covering the inspiration behind it. Lighting: North-light studio lighting, true color representation. Output: ONE image, 4:5, "artistic process" aesthetic. </instruction>

fighting with Nano Banana to make me the chronology of AI for this 2025.

A stunning photo prompt Gemini Nano Banana creation.

A stunning winter photo prompt Gemini Nano Banana creation.

Please make the room look clean and stylish after the year-end big cleaning.

{ "subject": "Classic three-ball snowman, highly textured snow", "clothing": "{argument name="hat color" default="Blue"} bucket hat (nylon texture), blue scarf (terry cloth texture)", "face": "Dark round stone eyes, orange carrot nose", "accessories": "Matching blue hat and scarf set", "environment": "Dark starry night sky, icy ground, high contrast", "lighting": "Dramatic cinematic spotlight, cool tones, accentuating textures", "camera": "Full shot, slightly low angle, sharp focus", "style": "3D render style, studio photography, minimalist, whimsical, photorealistic, 8k resolution" }

task": "image_to_image_style_transfer", "input_image": "{{USER_IMAGE}}", "prompt": "Create a hyper-real 3D studio composition that recreates the main subject from the provided image as a fragmented stone assemblage. The subject must be built from separate, clearly detached rock pieces with small visible gaps between shards (no pieces merging). Material look: fragmented {argument name="stone type" default="slate + sandstone"} shards with chiseled edges, crisp fractures, visible stone grain, micro-scratches, and realistic roughness. Color palette: predominantly dark slate with subtle warm-ochre sandstone accents. Lighting: soft studio key light from top-left, gentle fill, subtle contact shadows under each shard, realistic ambient occlusion in crevices, clean reflections kept minimal. Background: minimal off-white seamless backdrop, no texture. Framing: centered, clean, straight-on, subject fully readable. Add a few tiny debris chips floating or resting near the base for depth. Preserve the subject’s identity, proportions, and recognizable silhouette from the input image while transforming all surfaces into stone fragments. Hyper-real, high detail, sharp focus, 8k render quality.", "negative_prompt": "text, typography, logo, watermark, signature, extra props, busy background, fog, heavy bloom, cartoon, illustration, lowpoly, plastic, metal, glossy paint, melted shapes, merged fragments, unreadable subject, blur, noise, low resolution, oversharpening halos, distorted face/body, extra limbs, deformed geometry", "output": { "aspect_ratio": "use_input_aspect_ratio", "background": "off_white", "camera": { "angle": "straight_on", "framing": "centered", "distance": "medium" } }, "params": { "style_strength": 0.75, "identity_preservation": 0.9, "detail_level": "very_high", "lighting_preset": "soft_studio_top_left", "shadow_intensity": "subtle", "gap_visibility": "clear", "debris_chips": "few_tiny", "no_text": true } }

"Can you remove the noise cleanup the image and remove the small watermarks"

{ "metadata": { "engine_name": "PX-LOCK-X", "prompt_version": "pxlockx-1.0.0", "generation_goal": "Near pixel-perfect recreation with identity-only replacement", "reference_frame_policy": { "use_reference_as_ground_truth": true, "identity_swap_only": true, "no_creative_inference": true }, "units": { "angles": "degrees", "lengths": "centimeters", "coords": "normalized_0_to_1", "temperature": "kelvin" } }, "identity_replacement": { "mode": "identity_only", "reference_identity_source": "uploaded_subject_image", "replace": { "face_identity": true, "head_shape": true, "hair_color_and_length": true, "skin_tone": true, "body_identity": true }, "preserve_from_reference": { "pose": true, "camera": true, "lighting": true, "environment": true, "wardrobe": true, "jewelry": true, "expression_valence": true, "framing_and_crop": true }, "identity_strength": 1.0, "no_beautification": true, "no_style_transfer": true }, "output_settings": { "aspect_ratio": "2:3", "resolution_target": "reference_matched", "render_style": "photorealistic", "color_space": "sRGB", "compression": "lossless", "dynamic_range": "natural", "white_balance_lock": true }, "pixel_coordinates_lock": { "lock_enabled": true, "reference_frame_dimensions_px_estimate": { "width_px": 1024, "height_px": 1536 }, "crop_boundaries_px_norm": { "left_x_norm": 0.0, "right_x_norm": 1.0, "top_y_norm": 0.0, "bottom_y_norm": 1.0 }, "primary_subject_bounding_box_norm": { "x_min": 0.105, "y_min": 0.155, "x_max": 0.945, "y_max": 0.975 }, "head_bounding_box_norm": { "x_min": 0.205, "y_min": 0.175, "x_max": 0.625, "y_max": 0.360 }, "face_feature_anchors_norm": { "left_eye_center": { "x": 0.345, "y": 0.252 }, "right_eye_center": { "x": 0.445, "y": 0.247 }, "nose_tip": { "x": 0.405, "y": 0.287 }, "mouth_center": { "x": 0.403, "y": 0.318 }, "chin_point": { "x": 0.410, "y": 0.352 } } }, "camera_lock": { "lock_enabled": true, "camera_height_cm": 105.0, "camera_to_subject_distance_cm": 230.0, "camera_orientation_degrees": { "yaw": 8.5, "pitch": -3.0, "roll": 0.6 }, "lens": { "focal_length_mm": 85.0, "sensor_format": "full_frame", "distortion_model": "brown_conrady", "distortion_coefficients": { "k1": -0.012, "k2": 0.004 } }, "aperture": { "f_number": 2.2, "focus_distance_cm": 220.0, "focus_target": "face_plane" }, "exposure": { "iso": 200, "shutter_s": 0.002, "exposure_comp_ev": 0.0 } }, "pose_lock": { "lock_enabled": true, "pose_type": "deep_squat_crouch", "body_facin

{   "render_goal": "Contrasting fantasy portrait",   "subject": {     "pose": "female standing centered",     "expression": "controlled intensity",     "skin_tone": "fair warm glow"   },   "wardrobe": "{argument name="wardrobe item" default="ivory gown"} with soft {argument name="flame color" default="golden"} flames along the hem",   "environment": {     "location": "dark stone chamber",     "props": "floating embers, soft shadows"   } }

A massive {argument name="everyday object" default="[EVERYDAY OBJECT]"} casually used as temporary shelter by tiny {argument name="travelers" default="[TRAVELERS]"}. No construction, no permanence - just rest. Overcast lighting, soft shadows, intimate mood, naturalistic storytelling.

Change the style of this collage. make it in style of {argument name="painting style" default="cezanne painting"}, and add some small nature details, but keep the whole structure of {argument name="structural elements" default="stairs and animals"} intact.

"Change her outfit style: replace the blazer and short skirt with a slightly longer Santa-inspired dress that has a pleated bottom, in classic Christmas colors (red with white accents). Add a black belt with a large buckle. Instead of the Santa hat, add a large red bow on top of her head. Keep the same pose and all other elements unchanged."

"Transform the subject of the uploaded image into a watercolor illustration rendered in a distinct, stylized aesthetic. The artwork must feature strong, expressive contour lines defining the subject's features, hair, and clothing. The color palette is limited to fluid washes of {argument name="primary color" default="teal"}, muted {argument name="secondary color" default="coral/peach"}, warm beige, and sepia tones used for shading and highlights, replacing natural colors entirely. The final image should emphasize the texture of cold-press paper, visible paint granulation, and loose watercolor bleed effects. The subject's likeness must be preserved accurately within this new medium, set against a white paper background with abstract splashes of teal and coral watercolor"

I tried to create a cute and realistic-looking girl, and initially generated it with only instructions like “{argument name="initial instruction" default="beautiful Japanese woman"},” but the AI look inevitably remained like in the first image.... So, I tested what would happen if I restructured the prompt, focusing on a subject image that the AI could easily understand, rather than just atmosphere!

Eye color, eyelashes, clothing color, length, body line.

A band of tiny {argument name="characters" default="gnomes"} throwing a colorful festival on the rim of an enormous {argument name="everyday object" default="coffee mug"}. Paper lanterns strung on wire, confetti made from magazine scraps, warm ambient city-bokeh background, shallow depth of field, cinematic wide-angle close-up, vibrant saturated palette, tactile fabric and wood textures.