AI Image Prompts · 绘画提示词库

{argument name="character name" default="Aldric"}, a battle-worn medieval knight with {argument name="hair style" default="wet shoulder-length dark hair"}, scarred face, realistic steel armor covered in mud and rain, holding a bloodstained longsword, standing face to face with a {argument name="monster type" default="terrifying forest wraith"}, creature made of twisted bark, dead leaves and living darkness, glowing red eyes, crimson cracks glowing beneath its body, dark rainy forest, heavy rainfall, muddy ground, cinematic dark fantasy, dramatic lighting, ultra realistic, photorealistic, movie still, shallow depth of field, intense confrontation, atmospheric fog, epic fantasy, masterpiece.

The wings are composed of {argument name="material" default="mother-of-pearl"} wings, iridescent shell surface wings, pearlescent reflections on the wings, overlapping mother-of-pearl plates on the wings, layered decorative plates on the wings, wing-inspired plate work, decorative feather structure, stacked decorative plates on the wings, layered plate structure of the wings, luxurious decorative craftsmanship on the wings, three-dimensional layered details on the wings, and elegant decorative composition of the wings.

A surreal, photorealistic portrait of {argument name="character" default="[User Face/Character]"} standing naturally in a textured knit sweater. The head is seamlessly attached to the body. Surrounding the head is a large, transparent spherical bubble acting as a diorama. Inside this circular space is a highly detailed, miniature {argument name="theme" default="[Subject/Theme]"} environment, complete with tiny intricate props, rich lighting, and a tiny miniature version of the character. The main character's head sits naturally in the center of this spherical room. Cinematic volumetric lighting, sharp focus on the miniature details, minimal soft-gradient background. 8k, masterpiece

Photorealistic portrait of a {argument name="subject" default="young man"}(keep the facial features unchanged as uploaded image), exact facial identity preserved, beard, sharp jawline. (Outfit) Wearing {argument name="outfit" default="all-black streetwear, black oversized hoodie with minimal text, loose black wide-leg pants, dark sneakers, luxury black sunglasses"}.Pose) Head raised straight, dominant stance, shoulders squared, one hand relaxed near pocket, other hand slightly clenched, facing forward. (Supernatural Element) A massive {argument name="creature" default="black smoke demon"} standing directly behind him, glowing white eyes aligned above man's head, thick realistic smoke wrapping around shoulders and arms, smoke texture ultra-realistic, no cartoon style. (Environment) Minimal indoor background, dark wall, empty space, grey concrete floor. (Lighting) Dramatic low-key lightingsoft front light on face, deep shadows, cinematic high contrast. (Tech Specs) 8k resolution, aspect ratio 3:4, shot on 35mm lens, hyper-realistic, highly detailed texture. Negative Prompt: cartoon, anime, illustration, painting, 3d render, distorted face, changing face, reshaping face, beauty filter, smile, bright background, sunlight, car, city, messy, blur, noise, watermark, text, bad hands, extra fingers. Adjusting goggles with soft smile. Background is busy street.

A {argument name="setting" default="neon megacity transit control nexus"} in an {argument name="style" default="artistic cyberpunk style"}

{argument name="location" default="Abyss, bottomless pit, deep chasm"}

{argument name="event" default="Painting of a UFO falling"}

{argument name="style" default="Cyberpunk"}

Overall redraw and optimization of the image without changing the {argument name="original composition" default="original composition"}, {argument name="character pose" default="character pose"}, character design, original lighting effects, and lens relationship. Maintain the {argument name="illustration style" default="2.5D Japanese illustration style"}, but reconstruct the frame for a cleaner, more unified visual output. Perform global readjustment of color and lighting on the existing image so that the overall light and shadow relationship follows a single, stable lighting logic. Use a soft, uniform primary light source, avoiding layered shadows and fractured color blocks caused by multiple light sources. Shadow edges should transition naturally without hard boundaries or blocky filling. Unify material representation, ensuring continuous gradient structures in the color transitions of skin, hair, and clothing, reducing local noise, color block accumulation, and non-continuous shadow areas. Avoid any mosaic, dirty spots, or cloud-like color structures. The overall style should be within the high-quality 2.5D animation illustration range, with a slight sense of volume and soft spatial depth, but without introducing realistic skin textures, pore details, or photographic sharpening effects. Retain a moderate hand-painted feel and smooth color gradations. Reduce local high-frequency detail interference, avoid over-sharpened edges and excessive texture enhancement, and give the picture a clean visual fluidity and unified color rhythm. Keep character outlines and hair structures continuous, smooth, and consistent, avoiding edge jitter, breakage, or granular jaggedness. Lines should resemble stable hand-drawn animation line art rather than boundaries formed by local sharpening or noise stacking. Outline changes should transition smoothly without local 'jumps' or irregular fluctuations. Overall reduce microscopic contrast and local sharpening tendencies, keeping edge transitions soft for visual fusion. Avoid knife-cut hard edges or overly clear separation at the boundaries of skin, hair, and clothing. Highlights and shadows should be connected by flexible gradients rather than sharp-line structures. The overall look should be 'clear but not sharp,' retaining physical recognition while suppressing pixel-level sharpening marks. The final output should be a clear, soft, high-quality 2.5D illustration without regional contamination, featuring a stable lighting system, continuous line structures, and natural gradient transitions.

Create highly detailed, whimsical 3D rendering of a {argument name="subject" default="miniature Chibi cute girl"} sitting atop {argument name="object" default="mocha frappe cup"}, cute pose. A close-up, first-person perspective, a realistic female hand holds the cup and a phone in other hand, camera app is open, phone screen display live snapshot of the scene. Soft warm lighting, gentle bokeh, blurred cozy room background, shallow depth of field, 8K UHD.

Whimsical miniature world depiction of a {argument name="location" default="luxury hotel lobby"} in an artistic {argument name="style" default="arborpunk"} style.

A cinematic, hyper-realistic {argument name=\"theme\" default=\"cyberpunk soccer scene\"} set in a sprawling, rain-slicked futuristic metropolis at night. The environment features towering skyscrapers covered in massive glowing neon billboards, holographic displays, digital circuitry patterns etched into the ground, and flying cars streaking through the sky with light trails. A world-class professional {argument name=\"subject\" default=\"soccer player\"} is captured in a dynamic action pose—dribbling or kicking a soccer ball that surges with matching kinetic energy streaks and electrical currents. The player wears a custom futuristic tech-wear jersey adorned with glowing neon circuit patterns, their name, and number. The entire scene is unified by a distinct, vibrant {argument name=\"color scheme\" default=\"electric blue\"} that bathes the player and the city in a single dominant glowing light, creating a high-energy, sci-fi athletic aesthetic.

Hyper-realistic miniature diorama of {argument name="location" default="[TV LOCATION]"}, the building fills 70% of the frame, shot from a close elevated isometric angle, tilt-shift lens blur on foreground and background creating a miniature toy effect, golden hour warm lighting, highly detailed scale model aesthetic, surrounding environment visible but soft and secondary, large prominent {argument name="logo" default="[TV SHOW LOGO]"} in the top-left corner taking up 30% of image width, photorealistic render, cinematic quality, 4K, 4:5 aspect ratio

8K ultra-realistic cinematic. Turn this photo into a {argument name="target" default="character figure"}. Behind it, place a box with the character's image printed on it, and a computer showing the blender modeling process on its screen. In front of the box, and a round plastic base with the character figure standing on it. Set the scene indoors