GPT Image 1.5 Prompts

Create a retro vintage grainy but bright image of the reference picture. Use the uploaded image as exact facial reference, keeping the same features, proportions, and likeness. wearing a loose white shirt and dark trousers, is sitting on the ground with his back against the trunk of a bare tree. His eyes are closed and his head is tilted back slightly. He is in a grassy field with a line of trees in the background under a clear sky. The lighting is natural and soft, with a slightly desaturated color palette. keep my face 100% same as in reference image

create a realistic photo of her. 
Second try: make it even more realistic. like a real human with skin details. not art

{
  "meta_info": {
    "title": "Ethereal Hanfu Spirit",
    "style_category": "Chinese Fantasy / Abstract Digital Art",
    "aspect_ratio": "3:1"
  },
  "visual_elements": {
    "subject": {
      "description": "Silhouette wearing attire determined by the character",
      "pose": "Pose determined by the character, floating in mid-air",
      "composition": "Centered ethereal figure with flowing trails extending to the sides"
    },
    "atmosphere": {
      "lighting": "Bioluminescent glow, volumetric lighting, rim lighting",
      "effects": "Flowing smoke, light particles, holographic dispersion, silk-like energy trails",
      "colors": ["Deep Navy Blue", "Glowing Cyan", "Iridescent Gold", "Soft Peach"]
    }
  },
  "prompt_export": {
    "natural_language_prompt": "A wide panoramic digital artwork depicting a figure composed of flowing ribbons of light, translucent smoke, and iridescent particles. The background features deep, moody indigo and dark blue tones. The figure emits a soft, magical bioluminescent glow in hues of gold, peach, and cyan. The overall style is abstract fantasy, emphasizing fluid motion and a dreamy atmosphere, rendered in 8K resolution with highly detailed textures and exhibiting the Tyndall effect.",
    "tag_based_prompt": " silhouette, flowing light lines, smoke effects, particle effects, bioluminescence, iridescent effects, dark blue background, cinematic lighting, ethereal, mystical, masterpiece, best quality, 8k, wide angle --ay 21:9 ",
    "negative_prompt": "photorealistic, solid skin, heavy outlines, messy lines, text, watermark, low quality, jpeg artifacts, blurry, distorted face, bad anatomy"
  },
  "technical_settings_recommendation": {
    "sampler": "Euler a / DPM++ 2M Karras",
    "steps": 30,
    "cfg_scale": 7.0,
    "model_suggestion": "Niji 6 (for Midjourney) or Abstract/Fantasy-based SDXL models"
  }
}
Character set as: {argument name="character setting" default="The four master and disciples from Journey to the West"}

Cinematic fashion portrait of a young woman leaning against a vertical mirror in a grassy field. Symmetrical composition featuring her face and its sharp reflection. Natural daylight, soft skin textures, and an avant-garde deep red outfit. Calm, introspective mood with a shallow depth of field and editorial aesthetic.

Change the color of this character’s outfit to {argument name="color" default="red"}.

draw a realistic map of the U.S., with labels of all 54 states.

The woman in the first image should wear or put on all the elements from the second image.

Recreate this in a completely real world.

A male wearing a white shirt, black suit pants, and black leather shoes, in a {argument name="background" default="Paris street scene"}, with {argument name="lighting" default="bright sunlight"}, in a {argument name="style" default="fashion photography"} style.

Create an image about the very detailed steps you create to create the image.

Ultra-realistic cinematic photograph of a humanoid robot standing on a rooftop overlooking a modern city at dawn, medium shot. Highly detailed humanoid robot with synthetic skin and exposed metallic elements, realistic joints, fine mechanical details, subtle surface imperfections, micro scratches and reflections. Human-like posture and proportions, calm and natural stance, soft ambient light reflecting off metal and synthetic materials. Cinematic sunrise lighting, soft volumetric light, realistic city skyline in the background with shallow depth of field. A digital city billboard in the background displaying the text "{argument name="billboard text" default="SYSTEM ONLINE"}", text integrated into the screen with realistic glow, perspective, and lighting, not overlaid. Photorealistic futuristic photography, high fidelity materials, no cartoon style, no sci-fi illustration, production-ready realism.

A high-resolution, cinematic photograph of a lone, ancient lighthouse standing on a rugged cliff edge at sunset. The sky is dramatic, painted in deep oranges, purples, and blues, with rays of light breaking through the clouds. Waves crash violently against the rocks below, creating a fine mist. The lighthouse beam cuts sharply through the twilight air. The texture of the stone and the weathered metal of the lantern room are highly detailed. The overall mood is one of isolation, power, and enduring beauty. Shot on a large format camera, 85mm lens, f/2.8, golden hour lighting.

A long, over-engineered mechanical body dragging itself through a world it barely understands, cables everywhere like frantic neural pathways firing in the wrong direction, colours too bright, too fast, too messy. A head full of static mosaics and artificial light, glowing like it’s convinced it has a soul but glitching every time it tries to use it. Those tendrils — gods, the tendrils — they look like runaway thought-threads, each one pulling in a different direction, none of them connected to the body in any emotionally coherent way. Beautiful, chaotic, overstimulated, and utterly incapable of seeing where it’s going. And then there’s the posture. Dragging itself forward instead of walking. Half reaching, half collapsing.

Please add handwritten text ({argument name="date" default="2025.12.18"} + heart mark) and decorations to make it look like a Cheki (instant photo).

- I want a 4 panel image with a tea-cup falling and breaking, the 4 images will show it in various stages of falling breaking and shattering. 
- It is the same cup falling, so the cup must maintain consistency of the breaking parts and represent the physics correctly

in the same style as the image, generate a character sheet broken up into 5 separate sections divided by lines, the left section is a full front shot of the character head to toe, the other smaller sections are medium close up shots of the characters head and shoulders showing front, left, right and rear

an image of the day site

Give me this scene from 9 different angles in 3X3 1:1 grid, put the cell number at the left below corner of each scene

Maintain the character's style and outfit, change the scene to them intensely gripping a game controller, and create a thumbnail image in the style of a fictional VTuber's game stream.

They look a bit too robust, so please make them more delicate and cute. Also, the bust size should be more modest, and the sleeves should be long sleeves.

Fix the collapsed 'Ge' in the top left corner.

Based on a reference image, generate a multi-cut image with 9 cuts arranged within a single image.
The layout is a uniform 3x3 grid. Each cut must feature the same person, same composition, same pose, and same camera position.
Style specification for each cut (from top-left to bottom-right):
Cell animation style (TV anime style, clean line art, 2-3 levels of shading)
Theatrical anime style (delicate lines, rich gradient shading)
Black and white manga style (ink lines, screen tones)
Watercolor illustration (paper texture, bleeding, pale colors)
Oil painting (impasto, brushstrokes, canvas feel)
High-quality 3D cartoon (soft modeling, subsurface scattering)
Photorealistic 3D (PBR, texture close to real life)
Clay animation (clay texture, handmade feel)
Cyberpunk color grading (cyan/magenta rim lighting, background remains plain)
All 9 cuts must have perfectly identical composition, person, pose, and background, allowing only the style difference to be compared.
Arrange them naturally as a single finished image.

{
  "scene": {
    "location": "{argument name="location" default="Times Square, New York"}",
    "time": "{argument name="time" default="Rainy night"}",
    "composition": {
      "left_side": [
        {
          "type": "LED billboard",
          "style": "vertical",
          "text_color": "white-on-black"
        },
        {
          "type": "curved LED screen",
          "detail": "above yellow arrow for Hershey's store"
        }
      ],
      "right_side": {
        "subject_position": "near curb",
        "traffic": {
          "vehicles": "city taxis and cars",
          "details": "brake lights forming a slow line"
        }
      }
    },
    "environment": {
      "ground": "wet asphalt",
      "reflection_colors": ["neon magenta", "icy blue"],
      "puddles": {
        "reflecting_lights": true,
        "object_details": ["scattered takeaway cups"]
      },
      "atmosphere": ["electric", "intimate"]
    }
  },
  "subject": {
    "identity": "Uploaded subject",
    "face_requirement": "Do not change facial features. Must look 1000% identical.",
    "pose": "Relaxed, facing camera",
    "holding": "Folded black umbrella by handle",
    "outfit": {
      "jacket": {
        "material": "black faux-leather varsity",
        "design": {
          "cobalt_panel": true,
          "cream_stripe": true,
          "embroidery": "Vintage script",
          "lettering": "Block OF",
          "patch": "1987 stitched on sleeve",
          "reflective_piping": true,
          "highlight_color": "purple reflection"
        }
      }
    }
  },
  "background": {
    "elements": ["cars", "scaffolding", "stacked storefront signs"]
  },
  "style": {
    "resolution": "HD",
    "aesthetic": ["realistic", "natural", "authentic"],
    "camera": "iPhone"
  }
}

A highly precise design archive image of ancient Chinese architecture in the 'Yangshi Lei' style, themed as {argument name="theme" default="[theme]"}. The image uses a rigorous 'virtual-real deconstruction' composition: the background is old, gold-flecked Xuan paper with fiber texture, covered with meticulous line drawings of floor plans and cross-sections; the center features a scaled-down wooden 'tangyang' model, displaying extremely precise mortise and tenon joints and the natural wood color. Enhanced annotation logic: Clear vermilion lines pop out from key components of the model, pointing to text areas on the edge of the drawing, simulating authentic professional terminology annotations from the 'Yingzao Fashi' (Treatise on Architectural Methods). Enhanced professional layout: The edges of the image are adorned with vermilion seals unique to Qing Dynasty royal archives, precise scale markings, and neat vertical line-drawing borders, presenting an overall sense of order like a 'museum exhibit explanation poster'. Professional side-lighting from museum spotlights creates an extreme sense of material thickness and deep physical shadows. --ar 3:4

A candid, ultra-realistic documentary photograph capturing a poignant moment on a rain-soaked Galata Bridge in Istanbul, where an elderly fisherman with a deeply weathered face, wearing a patched oilskin jacket, laughs as he holds out a small fish to a drenched street cat balancing precariously on the railing beside his rusted tackle box. Rain streaks heavily. In the busy background, crowds of commuters with umbrellas are blurred by motion, a traditional city ferry crosses the choppy grey Bosphorus emitting smoke, and the silhouette of the New Mosque (Yeni Cami) rises under heavy, diffused storm clouds. The image has the distinct aesthetic of analog 35mm film grain, natural moody light, shallow depth of field focusing sharply on the man and cat, and highly detailed textures on wet pavement, old clothing, and metal.

A highly detailed, cinematic photograph of a lone, ancient samurai standing on a misty, rocky outcrop overlooking a vast, stormy sea. The samurai is wearing traditional, battle-worn armor, illuminated by a dramatic, pale moonlight breaking through the heavy clouds. The atmosphere is intense and melancholic. Medium resolution.