Shotcraft
Prompt craft · list

294 phrases for image prompts, grouped by the decision each one controls

294 phrases across 24 decisions, in the order they go in the prompt. Each group names the decision it controls, so when a result is wrong you change one group instead of rewriting the prompt. Free PDF at the bottom, no sign-up.

The problem

Image prompts collect adjectives until nobody, including the writer, can tell which word is doing the work — and when the result drifts, there is no way to know what to remove.

What this gives you

Sorted into the decisions a still actually has: subject, framing, optics, light, surface, grade. Add one phrase per decision and stop.

Skip to the PDF · Image prompts explains what each group does

Aspect ratio

7 entries · Frame shape.

Square 1:1.

Vertical 4:5 for a feed post.

Medium and style

15 entries · Photograph, render, illustration or something else.

Photorealistic editorial photograph.

Clean 3D product render on a seamless backdrop.

Shot size

10 entries · How close the camera is.

Extreme close-up, texture filling the frame.

Full body shot, head to feet, room above and below.

Camera angle

9 entries · Viewing position.

Three-quarter view, turned slightly off axis.

Straight-on profile, subject facing frame left.

Composition and framing

10 entries · Where things sit in the frame.

Centred on a single vertical axis, symmetrical.

Rule of thirds, subject on the right third, negative space left.

Lens and focal length

22 entries · Perspective and compression.

85mm portrait lens, natural compression.

35mm, mild environmental context around the subject.

Depth of field

12 entries · Focus falloff.

Shallow depth of field at f/1.8, background soft.

Everything sharp front to back, deep focus.

Lighting

22 entries · Direction, quality and source of light.

Large softbox front left, soft shadows falling right.

Backlit into silhouette, subject dark against a bright field.

Colour and palette

11 entries · Palette, saturation, contrast.

Vibrant, fully saturated, clean whites.

Muted pastel palette, soft contrast.

Materials and finish

14 entries · What surfaces are made of.

Brushed metal with a satin finish, no mirror reflections.

Matte ceramic, slightly uneven glaze.

Mood

14 entries · The feeling.

Elegant and restrained.

Playful and bright.

Subject + setting + style (the opening clause)

2 entries · "Higgsfield models reward concrete, sensory prompts." app-cover.md wants the product's core verb staged as a physical, photographable moment.

a red fox curled in a snowy pine forest, golden hour, cinematic

a film editor in a bold red bomber jacket mid-leap, cutting a giant arc of 35mm film with oversized chrome scissors

Typography named in the prompt (when text is generated)

25 entries

The prompt must state: Exact literal copy; Display/body font family names and which text uses each

Name the exact display/body families in the prompt; never infer typography from the logo or palette.

Identity lock / subject fidelity

5 entries · Up to three referenced identities; face photos are passed first in character order, then the logo, and a manifest line must open the prompt when two or more references are attached.

CHARACTER N: the person from attached face reference #K, IDENTITY LOCK: reproduce this exact person with a photographic identity match, same bone structure, eye shape, nose, lips, jawline, skin tone, hairline and hair texture. Do not beautify, average, or restyle the face. Expression: <emotion phrase>.

IMAGE REFERENCES: image 1 = CHARACTER 1 face reference; image 2 = brand logo.

Aesthetic / seasonal preset

14 entries · These are the labelled options the skill offers for restyle and style/mood questions; they become the short intent line handed to the backend enhancer.

Christmas version, quiet-luxury aesthetic

vertical pin for my candle brand, cottagecore mood

Product-photo genre / mode

10 entries · For both skills the user-facing prompt is a short intent line only, "Backend assembles the final prompt; never freehand it." `--count 3` makes the backend vary preset, lighting, angle and palette across variants.

bottle of cold-brew on a sunlit kitchen counter, IG feed

sparkling peach lemonade can for marketplace listing

Logo / vector mark specification

14 entries · One central visual idea per mark, stated in one clause; the exact phrase "no text" must appear in the constraint tail; mark_type routing is evidence-based, defaulting to abstract, never wordmark or combination mark.

Flat vector design, clean lines, no shadows, no texture, no text. Clean editable vector paths, SVG-friendly, minimal anchor points.

Monoline vector design, uniform stroke weight, rounded line caps, no fills, no shadows, no texture, no text. Clean editable vector paths, SVG-friendly, minimal anchor points.

Logo placement on a mockup surface

11 entries · Full-colour marks go on smooth surfaces; black monochrome on light kraft paper, natural cardboard, pale fabric, stamps, dark-ink screen printing, engraving masks and light uncoated stock; white monochrome on dark paper/boxes/fabric, reverse marks, light-ink screen printing and dark signage.

[PLACEMENT LOCK] Target surface: <exact object panel/face/material>. Position: <exact alignment and location, e.g. horizontally centered, upper third, optical center aligned to panel>. Scale: logo occupies <specific proportion> of the target surface while keeping <specific clear-space margin>. Orientation: align to <panel edge/seam/baseline>; follow surface perspective without changing logo proportions. Color: use the supplied <full-color/black/white> variant exactly. State why it contrasts correctly with the material/background.

[AUTHORITATIVE LOGO] <ImageN> is the exact approved <full-color/black/white> logo. Preserve its spelling, silhouette, geometry, proportions, internal negative space, and exact color. Do not redraw, simplify, crop, stretch, outline, or add effects.

Seamless / tileable behaviour

7 entries · {MATERIAL} in the texture templates is 3-6 concrete words from the reference, e.g. "hand-painted cracked dry earth with small grey stones".

seamless tileable game texture tile of <description>, uniform pattern density,

, perfectly seamless edges that wrap horizontally and vertically, no border, no vignette, flat even lighting, no single focal object

Key colour for transparency

3 entries · Models cannot output alpha, so asking for "transparent background" produces a fake checkerboard. Default magenta; switch to green if the subject's own colours are near pink/magenta/purple; blue if both are taken. The chosen colour must appear in both the prompt suffix and the keying script.

on a solid uniform bright <KEY COLOR> background, crisp edges, no drop shadow outside the element

Clean uniform <key color> background.

Reference-image role and what it controls

9 entries · For image-to-image the prompt should describe what changes, not redescribe the input: bad "a man with brown hair in a leather jacket holding coffee, made into anime"; good "transform into anime style, vibrant colors, soft cel shading".

Make an Animated Explainer. Take only the visual render style and color grading of the input image(s); mix the styles if there is more than one image. Never use the characters, inscriptions, etc. from the input image(s) unless the instructions below ask you to. Use only the render style, and follow the user's instructions below:

Use references as style donors only. Never copy their people, text, logos, or objects.

Design-board direction vocabulary (web/layout imagery)

26 entries · Commit to one option per category before prompting and hold it across all boards; one board per section, landscape 16:9 or 3:2, never one tall full-page image.

"website design mockup, desktop landing page section, [SECTION ROLE], [theme paradigm + exact palette words], [typography character] typography, [hero architecture / composition anchor], [background mode], [narrative spine motif], professional layout, clear hierarchy and spacing, award-winning web design", plus: "no watermark, no browser chrome".

Name real content in the prompt (the actual headline wording you plan) so type sits believably.

Reference photos for identity training

14 entries · 5-20 photos, 8-12 the sweet spot, clear face with eyes visible, single person per photo, sharp, ≥1024×1024 ideal.

Higher variety = better identity capture.

Image-to-3D input framing

8 entries · One figure per input image, a 4-view character sheet reconstructs as "a statuette of 4 fused figures".

Full body in frame, nothing cut off.

Clean/plain background; no shadows, text, watermarks, logos.

Free, no sign-up, no email

All 294, as a PDF

Every entry on this page, in the same order, over 3 printable pages. Nothing is trimmed to make it fit — the count in the title is the count in the file.

Download the PDF 3 pages · A4 · 10 KB · generated 2026-09-01

The web page is the version that gets corrected. A sheet printed six months ago has not moved. All downloads.

Common questions

What makes a good AI image prompt?

One phrase per decision and no repetition. A prompt naming subject, framing, optics and light in four clear clauses beats a paragraph of twenty adjectives, because the adjectives compete and the model averages them.

Should I use negative prompts for images?

Only where the model has a negative field. Most media models do not, so a banned word is still a word in the prompt. Say what you want instead: 'tack sharp' rather than 'no blur'.

Where this comes from, and what to read next

This page is a list. It does not explain the material — Image prompts does, group by group, with what each decision controls and why. Research on how people actually prompt is collected under how people really use AI.

Prompt craft · Models · Cinematic language · Downloads