Find your next good prompt.

Character reference sheet, single subject repeated across a clean grid, 6 panels on a neutral light grey seamless background (#e6e6e6).

SUBJECT: 28-year-old [gender] with [hair colour and cut], [eye colour] eyes, [skin tone] skin, [one distinctive permanent feature: freckles across nose / small scar above left eyebrow / silver septum ring], wearing [exact outfit: charcoal wool overcoat, black crew neck, dark denim].

PANELS: front full body, three-quarter left, profile left, back, waist-up neutral expression, waist-up subtle smile.

Consistent flat studio lighting from a large softbox at 45 degrees camera left, no coloured gels, no shadows on the background. Shot on 85mm lens, f/5.6, sharp focus edge to edge, photorealistic skin texture with visible pores, natural colour grading.

Identical face geometry, identical hairstyle, identical wardrobe in every panel. No text, no watermarks, no logos, no additional people, no props.

Aspect ratio: 3:2.

Using the attached reference image as the exact identity, generate a new photorealistic portrait of the same person. Do not change facial structure, eye shape, nose, jawline, hairline, or skin tone.

NEW SCENE: [describe: standing on a rain-soaked city street at night, neon signs reflecting in puddles behind them].
WARDROBE: [describe exactly].
LIGHTING: soft key light from camera left, cool rim light from behind right, practical neon sources visible in the background bokeh.
CAMERA: 50mm lens, f/1.8, shallow depth of field, subject sharp, background compressed and blurred.
FINISH: natural skin texture with pores and fine hairs visible, no beauty smoothing, no plastic sheen, subtle film grain, colour graded with cool shadows and warm highlights.

Keep the identity 100% consistent with the reference. Photorealistic, editorial photography quality, 4K detail.

Convert the attached anime character into a photorealistic real human being while preserving every design signature.

PRESERVE: exact hair colour and silhouette, eye colour, outfit design and colour palette, accessories, signature pose, and overall vibe.
TRANSLATE: stylised proportions into realistic human anatomy, flat cel shading into real subsurface-scattering skin, anime eyes into realistic eyes of the same colour with matching intensity.

RENDER AS: full body editorial photograph, shot on 85mm at f/2.0, studio three-point lighting with a soft key camera left and a coloured rim light matching the character's dominant accent colour, dark neutral backdrop.

Photorealistic skin texture, real fabric weave and stitching on the costume, realistic hair strands with flyaways, cinematic colour grade. No cartoon lines, no cel shading, no text.

Aspect ratio: 2:3.

A cartoon horror illustration: [describe creature, e.g. a grinning porcelain doll with too many teeth and hollow button eyes], drawn in a 1930s rubber-hose animation style corrupted into nightmare fuel.

STYLE: thick confident ink outlines, limited palette of bone white, dried blood red and deep charcoal, heavy film-scratch texture and vignette like a damaged reel.
COMPOSITION: creature centre frame, slightly low angle so it looms over the viewer, empty negative space around it.
LIGHTING: single harsh light source from below, long distorted shadow thrown up the wall behind.
MOOD: unsettling, uncanny, silent — the moment before it moves.

No gore, no blood spatter, no text, no watermark. High detail, print quality.

Aspect ratio: 16:9.

First-person POV pixel art game screenshot, 32-bit era aesthetic.

SCENE: [describe, e.g. standing at the entrance of a flooded subway tunnel, torchlight ahead].
UI: retro HUD along the bottom — heart containers top left, stamina bar, an inventory hotbar of 6 slots, small minimap top right.
PALETTE: 24 colours maximum, dithered gradients, strong contrast between lit and unlit areas.
DETAIL: crisp pixel edges, no anti-aliasing, no blur, visible pixel grid, subtle CRT scanline overlay.

Composed as a real playable frame, not concept art. No modern typography, no photorealism.

Aspect ratio: 16:9.

Photorealistic lifestyle photograph of the same person as the attached reference. Identity must remain identical — same face, same hair, same body proportions.

SCENE: [e.g. sitting at a corner table in a sunlit Lisbon café, iced coffee on the table, tiled wall behind].
WARDROBE: [exact outfit].
POSE: candid, mid-gesture, looking slightly off camera, natural body language, not posed for the lens.
CAMERA: 35mm lens, f/2.2, eye level, subject placed on the right third.
LIGHT: warm natural window light from camera left, soft falloff, gentle highlight on the cheekbone.
FINISH: real skin texture with pores and fine hair, slight lens vignette, natural colour science like a Fujifilm sensor, no beauty filter, no HDR look.

Instagram editorial quality, believable as a real photo. No text, no logos, no extra hands or fingers.

Aspect ratio: 4:5.

Using the attached photo of a room as the exact base, generate the transformed "after" version.

KEEP IDENTICAL: room dimensions, window positions and shapes, door placement, ceiling height, and the camera angle and lens of the original photo.
CHANGE TO: [target style, e.g. warm Japandi — oak flooring, off-white lime-wash walls, low linen sofa, paper pendant lamp, three potted plants, minimal styling].
LIGHTING: golden hour daylight entering through the existing window, soft bounce fill, realistic contact shadows under every object.
RENDER: architectural interior photography, 24mm lens, f/8, verticals perfectly straight, photorealistic materials with accurate reflections and texture.

No people, no text, no floating furniture, nothing that ignores the original room geometry.

Aspect ratio: 3:2.

Upscale and restore the attached image to 4K resolution.

DO: reconstruct fine detail in skin pores, individual hair strands, fabric weave, and background texture; remove compression artefacts, banding and colour noise; recover shadow detail without lifting the black point; sharpen edges naturally.
DO NOT: change the subject's identity, facial proportions, expression, pose, wardrobe, framing, or colour grade. Do not add jewellery, makeup, or background objects that were not there. Do not smooth skin into plastic.

Output a photorealistic, print-ready image that looks like the original was shot on a higher resolution sensor. Preserve natural film grain at a reduced level.

Design a YouTube thumbnail image, 1280x720.

CONCEPT: [describe the single idea the thumbnail must communicate in under one second].
COMPOSITION: hero subject filling the left 60% of frame, strong negative space on the right for text placement, subject facing into the space.
CONTRAST: subject separated from the background by a bright rim light and a deep dark background; the two brightest points in the image are the subject's face and the focal object.
PALETTE: two dominant colours plus one high-saturation accent used only on the focal object.
STYLE: photorealistic, high micro-contrast, slight vignette, colour graded for punch on a small screen.

Legible at 200px wide. No text in the image itself, no borders, no watermark, no clutter in the background.

Aspect ratio: 16:9.

Generate a cohesive set of 6 cinematic b-roll still frames for a faceless video about [TOPIC].

Shared look across all six: same colour grade ([describe palette]), same lens character ([focal length], shallow depth of field), same time of day, same atmospheric condition (haze / rain / dust).

The six frames:
1. Establishing wide, subject small in frame.
2. Medium detail of a hand interacting with an object.
3. Extreme macro texture detail.
4. Silhouette against a light source.
5. Overhead top-down composition.
6. Slow-shutter motion abstract.

Photorealistic, no people's faces visible, no text, no logos. Each frame must cut together with the others without a grade mismatch.

Aspect ratio: 16:9.

Generate a background plate designed for text to be placed on top of it.

SCENE: [describe, e.g. dark volumetric fog rolling across a black void with a single cool blue light source top left].
COMPOSITION: the centre 60% of the frame must stay visually quiet — low detail, low contrast — so overlaid text remains readable. All visual interest sits in the outer thirds.
CONTRAST: overall dark, exposure held below mid-grey in the centre.
DETAIL: subtle grain, gentle gradient falloff, no busy patterns, no hard edges crossing the centre.

No text, no subject, no logos, no watermarks.

Aspect ratio: 9:16.

Generate a 6-panel storyboard for a faceless short.

STORY: [PASTE the beat in one sentence]

Render as a 2x3 grid of rough greyscale storyboard panels on white, drawn in loose marker-and-pencil style with quick hatching for shadow.

For each panel show: the framing (wide / medium / close), the subject staging, and arrows indicating camera movement or subject movement.

Panel beats: establish, approach, discovery, reaction, escalation, resolution.

Keep the same character silhouette in every panel. Rough and fast, not polished illustration. No colour, no text, no panel numbers drawn in the image.

Aspect ratio: 3:2.