AI Prompts
Generative AI with AI Tools
AI Prompt - Text to Image

Adobe Firefly Image 3
(Text-to-Image prompt)
A Biomorphic Holographic Bloom illustration of Common Kingfisher, where organic forms and flowing lines are infused with a shimmering, iridescent holographic effect. Feature translucent, petal-like structures and a color scheme centered around luminous luminous rose pink and sky blue hues.

Adobe Firefly Image 3
(Text-to-Image prompt)
A solitary leopard sits on a tree branch with vivid and shiny colours.

ChatGPT Image 1
(Text-to-Image prompt)
Create new 3D caricature of my pet cat sitting at corner of my home.

ChatGPT Image 1
(Text-to-Image prompt)
Create an ultra-realistic and luxurious professional image of a detailed action figure modeled exactly after me. The figure is packaged within a premium, elegant display 3D box with a transparent viewing window. The 3D box itself should evoke luxury, featuring visibly raised print (embossed lettering) to enhance texture and sophistication. The embossed text should include “Super Mini BKoh” prominently at the top and “AI Tools Coach” at the bottom, adding an upscale collectible feel. The figure must appear genuinely plastic with precise and realistic molding, clearly visible seams, glossy or semi-glossy plastic finish, and articulation points. This must be a full body action figure. He has distinctively brown eyes, and nice straight, white teeth, smiling. on the box should be the words “NEW” and “Ages 18+”. Within the box, alongside the figure, display realistic and scaled miniature accessories relevant to my personality and interests: …

ChatGPT Image 1
(Text-to-Image prompt with reference)
… a Blue Yeti style microphone, DSLR camera, laptop, and headphones. The box should have a refined color palette and visually appealing design elements, clearly targeting adult collectors. Utilize professional, soft, even studio lighting to accentuate the luxurious textures and realistic materials of both the figure and the embossed box details. The final image should emulate the refined aesthetic and premium quality of high-end collectible product photography, taken in a studio. Crisp and sharp focus captured with Canon EOS R5, 85mm lens, slight depth of field, authentic commercial product appearance. The package is on a white background, casting subtle shadows from the studio lighting and some slight reflection on the box itself. The inside of the box and it’s contents should also be sufficiently and professionally lit, so they can be seen.

ChatGPT Image 1
(Text-to-Image prompt with reference)
Transform this reference photo into an ultra-realistic, highly detailed 3D caricature with a lifelike, expressive finish. Preserve and emphasize the subject’s unique facial structure, skin texture, hairstyle, clothing, and posture with extreme precision. Ensure the final result remains instantly recognizable and faithful to the original image, maintaining the distinctive character traits and mood. Highlight exaggerated expressions and a stylized, oversized head while using micro skin details (like pores, wrinkles, and facial lines), and lifelike fabric textures. The style should resemble high-end animated film characters.
ChatGPT Image 1
(Text-to-Image prompt with reference)

ChatGPT Image 1
(Text-to-Image prompt with reference)
Again, using the 1st reference image and adopt this style: Convert this image into a Classic Disney character style, in ultra-realistic Classic Disney rendering with smooth stylized textures, detailed fabric and hair modeling and identical but expressive facial features set against a clean background, in the style of high-end CGI character portrait.

ChatGPT Image 1
(Text-to-Image prompt with reference)
Again, using the 1st reference image and adopt this style: Transform this image into a high-quality vector art illustration. Emphasize a clean, modern vector style using flat, solid-color fills and smooth, geometric forms. Define the subject with precise, consistently weighted contour lines that subtly vary to retain natural facial proportions and distinct feature shapes. Apply a color palette that matches the original image colors. Strictly avoid gradients, textures, or noise. Ensure all edges are crisp and anti- aliased, with a polished, professional finish suitable for editorial digital illustrations.

Gemini 2 – Nano Banana
(Text-to-Image prompt)
Photorealistic of a elegant Japanese sushi platter beautifully arranged on a dark ceramic plate, fresh nigiri and sashimi with vibrant colors, wooden table setting, soft cinematic restaurant lighting, high-end food photography, detailed textures, studio-quality image, in the style of hyper-realistic, Fuji film x-t4, Majestic lighting, soft lighting, hyper realistic look, octane, Impressive textures, 8k f/2.8, Kodak Portra 800, 70mm cinematic style, full-length shot, film grain.

Perplexity – ChatGPT Image 1
(Text-to-Image prompt)
A whimsical, cozy scene set inside a hollowed-out, old bread loaf turned into a tiny library. 3D realistic style. The interior is warmly lit with soft yellow light glowing from small jam jars used as lamps. Miniature people sit on slices of toasted bread, using pats of butter as soft pillows while quietly reading tiny books. Shelves carved into the bread walls are lined with miniature novels, tea bags, and biscuit covers as book spines. 16:9 aspect ratio for YouTube dimension.

Perplexity – ChatGPT Image 1
(Text-to-Image prompt)
Fit muscular man in his 50s working out with battle rope, side camera shot, wearing white stringent shirt and navy blue shorts, smiling.

Midjourney 6
(Text-to-Image prompt,
Firefly Image 3 – Generative Fill)
A low angle photograph capturing the grandeur of an ancient castle amidst falling snow, reflecting a gloomy atmosphere. –ar 16:9

Midjourney 6
(Text-to-Image prompt,
Firefly Image 3 – Generative Fill)
A dark, gothic portrait of a tattooed nun with a modern edge, smoking a cigarette. She wears traditional black nun attire with a flowing veil, her hands adorned with intricate tattoos. A glowing red halo encircles her head, casting an eerie contrast against the dark background. Her calm yet defiant expression is framed by tendrils of smoke drifting around her face. A large gold cross necklace rests on her chest, reinforcing the blend of religious and rebellious themes. Dramatic, moody lighting with deep shadows and rich texture, high detail, cinematic realism.
ChatGPT Image 1.5 (Text-to-Image prompt) & Firefly Image 3 – Generative Fill
A cinematic shot of this stunning Wat Rong Khun temple, its pristine white structure adorned with intricate gold and vibrant blue decorations. The temple stands prominently against a backdrop of lush green hills and dense forests. The camera provides a panoramic view as it displays temple’s unique architecture, highlighting the interplay of light and shadow. The scene is set against a clear blue sky with a few scattered clouds, enhancing the temple’s ethereal beauty. The image style is crisp and vibrant, capturing the temple’s intricate details and the serene natural surroundings in a high-definition format. There are no people walking around the premises; only showing the temple at its glorious moments of display.
ChatGPT Image 1 (Text-to-Image prompt with reference)
Using the 1st reference image and adopt this style: Change this image into a loose, minimal, black line art. Use thin, spontaneous, sketchy pen strokes to draw a cartoony-like, caricature style, with stylized, gentle, expressive line weight variations. Emphasize natural sketch randomness, with playful drawing, and no shading. Clean white background with expressive, imperfect strokes that suggest form without rigid precision. Professional cartoon sketchbook aesthetic.
ChatGPT Image 1 (Text-to-Image prompt with reference, Firefly Image 3 – Generative Fill)
Transform this reference photo into an ultra-realistic, highly detailed 3D caricature with a lifelike, expressive finish. Preserve and emphasize the subject’s unique facial structure, skin texture, hairstyle, clothing, and posture with extreme precision. Ensure the final result remains instantly recognizable and faithful to the original image, maintaining the distinctive character traits and mood. Highlight exaggerated expressions and a stylized, oversized head while using micro skin details (like pores, wrinkles, and facial lines), and lifelike fabric textures. The style should resemble high-end animated film characters.
ChatGPT Image 1 (Text-to-Image prompt with reference, Firefly Image 3 – Generative Fill)
Create an ultra-realistic and luxurious professional image of a detailed action figure modeled exactly after me. The figure is packaged within a premium, elegant display 3D box with a transparent viewing window. The 3D box itself should evoke luxury, featuring visibly raised print (embossed lettering) to enhance texture and sophistication. The embossed text should include “Super Mini BKoh” prominently at the top and “AI Tools Coach” at the bottom, adding an upscale collectible feel. The figure must appear genuinely plastic with precise and realistic molding, clearly visible seams, glossy or semi-glossy plastic finish, and articulation points. This must be a full body action figure. He has distinctively brown eyes, and nice straight, white teeth, smiling. on the box should be the words “NEW” and “Ages 25+”. Within the box, alongside the figure, display realistic and scaled miniature accessories relevant to my personality and interests: a Blue Yeti style microphone, DSLR camera, laptop, and headphones. The box should have a refined color palette and visually appealing design elements, clearly targeting adult collectors. Utilize professional, soft, even studio lighting to accentuate the luxurious textures and realistic materials of both the figure and the embossed box details. The final image should emulate the refined aesthetic and premium quality of high-end collectible product photography, taken in a studio. Crisp and sharp focus captured with Canon EOS R5, 85mm lens, slight depth of field, authentic commercial product appearance. The package is on a white background, casting subtle shadows from the studio lighting and some slight reflection on the box itself. The inside of the box and it’s contents should also be sufficiently and professionally lit, so they can be seen.
ChatGPT Image 1 (Text-to-Image prompt with reference, Firefly Image 3 – Generative Fill)
Create an ultra-realistic professional image of a detailed plastic action figure modeled precisely after me in this image. The action figure should appear genuinely made from plastic, clearly showcasing realistic molding, seams, articulation points, and a glossy or semi-glossy plastic finish, giving it a true commercial action figure look. The figure is standing upright, presented in a transparent blister pack with professional retail-style packaging. Include realistic miniature plastic accessories: a microphone, DSLR camera, headphones, and laptop, each clearly visible and scaled proportionately to the figure. The packaging features dynamic, professional graphics with vibrant colors and prominently displays the text “Mini BKoh Action Figure”. Also on the packaging have “Ages 18+” and NEW in the corner. Use bright, even studio lighting to enhance the realistic reflections and plastic textures of the figure and accessories, and capture the scene using the aesthetic style of product photography found in professional advertising.
ChatGPT Image 1 (Text-to-Image prompt with reference, Firefly Image 3 – Generative Fill)
Again, using the 1st reference image and adopt this style: Transform this image into a high-quality vector art illustration. Emphasize a clean, modern vector style using flat, solid-color fills and smooth, geometric forms. Define the subject with precise, consistently weighted contour lines that subtly vary to retain natural facial proportions and distinct feature shapes. Apply a color palette that matches the original image colors. Strictly avoid gradients, textures, or noise. Ensure all edges are crisp and anti- aliased, with a polished, professional finish suitable for editorial digital illustrations.
ChatGPT Image 1 (Text-to-Image prompt with reference, Firefly Image 3 – Generative Fill)
Again, using the 1st reference image and adopt this style: Convert this image into a Classic Disney character style, in ultra-realistic Classic Disney rendering with smooth stylized textures, detailed fabric and hair modeling and identical but expressive facial features set against a clean background, in the style of high-end CGI character portrait.
Adobe Firefly Image 3 (Text-to-Image prompt)
A Biomorphic Holographic Bloom illustration of Common Kingfisher, where organic forms and flowing lines are infused with a shimmering, iridescent holographic effect. Feature translucent, petal-like structures and a color scheme centered around luminous luminous rose pink and sky blue hues.
Gemini 3 Pro (Text-to-Image prompt) & Firefly Image 3 – Generative Fill
Wild and powerful Chinese legendary beast, primal stance, muscular build, sharp claws and teeth, tribal Chinese patterns engraved on body, fire and smoke effects, glowing eyes, jungle or stormy sky background, intense lighting, hyper-detailed animal art.
Gemini 3 Pro – Nano Banana (Text-to-Image prompt)
A wide-full view scene featuring a cherry blossom tree with petals gently falling, designed for a mood board. The blossoming petals should be vivid, colorful and full. Spelling and typo of the words in the pin up notes are to be correct and precise, not nonsense text. A brunette teen girl front view in a flowy plain white dress stands beneath it, evoking a cinematic, wallpaper-like photoshoot with a super girly and feminine aesthetic. 16:9 format only.
Gemini 3 Pro – Nano Banana (Text-to-Image prompt)
Design an embroidered denim fabric that combines lace and crystal, presenting blue lilies. This design gives the front a delicate feel, with a deep indigo background decorated with randomly placed flowers and leaves. The petals are delicately embroidered with ivory to enhance their three-dimensional and tactile feel, and each flower has two gold beads at its core.
Gemini 2 – Nano Banana (Text-to-Image prompt)
A collage featuring three Gen Z/Millennial ladies (18-39 years old) on a beautiful seaside setting with morning sun, each carrying a crescent shoulder bag like the one pictured, but in three distinct colors. The women should be depicted in different standing or seated poses, with the shoulder bags clearly visible on their shoulders.
Gemini 2 – Nano Banana (Text-to-Image prompt)
A close-up shot of the young woman’s upper torso and arm, holding the vibrant orange structured shoulder bag. The camera angle is from a slightly elevated perspective, looking down, as she holds the bag casually against her hip, showcasing its front. The focus is critically sharp on the bag’s sleek hardware (the distinctive clasp and any buckles/accents) and its structured, boxy silhouette. She is styled with her pastel orange linen dress. The backdrop is a clean, modern, architectural surface (e.g. a subtly shadowed, light grey concrete or off-white wall) to make the vibrant orange product pop. This shot emphasizes the contemporary, runway-inspired element of the bag.
Gemini 2 – Nano Banana (Text-to-Image prompt)
An extreme close-up of the young lady’s feet, now in a seated pose, with the camera positioned to the right, looking towards her left foot. Her feet are elegantly positioned, showcasing the vibrant orange Charles & Keith strappy sandals on a textured surface (e.g., a modern, light-colored wooden bench or concrete step). The shot should clearly highlight the intricate woven details of the straps and the unique lacing, with her feet pointed gracefully towards the left. A sliver of her pastel orange dress fabric is visible to maintain context. Use crisp focus and soft, natural light to emphasize the material quality and the rich colour of the sandals.
Midjourney 6 (Text-to-Image prompt, Firefly Image 3 – Generative Fill)
Capture a photograph of an abandoned warehouse at night using a long exposure while a person moves through the frame with a flashlight, creating dynamic light painting effects against the dark backdrop. –chaos 10 — ar16:9 –stylize 150
Midjourney 6 (Text-to-Image prompt, Firefly Image 3 – Generative Fill)
Hyper-realistic close-up photograph of an intricately crafted porcelain bee, its delicate body adorned with blue and white porcelain patterns and gold filigree accents. The bee rests against a deep black background, illuminated by precise studio lighting that enhances volumetric depth and ray-traced reflections. The piece blends surrealism with fine craftsmanship, in the artistic style of Marc Simonetti.
Midjourney 6 (Text-to-Image prompt, Firefly Image 3 – Generative Fill)
A dark, gothic portrait of a tattooed nun with a modern edge, smoking a cigarette. She wears traditional black nun attire with a flowing veil, her hands adorned with intricate tattoos. A glowing red halo encircles her head, casting an eerie contrast against the dark background. Her calm yet defiant expression is framed by tendrils of smoke drifting around her face. A large gold cross necklace rests on her chest, reinforcing the blend of religious and rebellious themes. Dramatic, moody lighting with deep shadows and rich texture, high detail, cinematic realism.
Perplexity – Gemini 3 Pro (Text-to-Image prompt) & Firefly Image 3 – Generative Fill
Giant lotus made of volcanic stone, each petal cracked and fractured, glowing lava flowing from within the cracks, layered molten lava streaming down from the petals, placed in a vast apocalyptic lava plain, glowing magma pools around the base, cracked scorched earth, steam rising, dark moody atmosphere, surreal fantasy landscape, cinematic lighting, high detail, epic scale, dramatic composition, concept art.
Perplexity – Gemini 3 Pro (Text-to-Image prompt) & Firefly Image 3 – Generative Fill
A hooded guardian clad in weathered armor and a torn forest-green cloak, standing in a dynamic pose with a spear resting on his shoulder. His silhouette contains a double exposure of abandoned ruins, moonlit mountain paths, hidden altars, and a ghostly figure cloaked in blue flame. Misty fog surrounds his lower body, enhancing the silhouette effect. Cinematic composition, ethereal mood, sharp realism, stylized in Octane Render + Unreal Engine look, high contrast and depth.
Perplexity – ChatGPT Image 1 (Text-to-Image prompt)
A whimsical, cozy scene set inside a hollowed-out, old bread loaf turned into a tiny library. 3D realistic style. The interior is warmly lit with soft yellow light glowing from small jam jars used as lamps. Miniature people sit on slices of toasted bread, using pats of butter as soft pillows while quietly reading tiny books. Shelves carved into the bread walls are lined with miniature novels, tea bags, and biscuit covers as book spines. 16:9 aspect ratio for YouTube dimension.
































