Floniks
Prompt Writing

Prompting Coffee and Beverages

Updated 2026-06-19·11 min read
Key takeaway

Coffee and beverage photography demands mastery of liquid surface rendering, steam and condensation physics, glassware transparency, crema texture, and the warm lifestyle context that makes a single cup image resonate emotionally. AI models consistently fail at crema detail, convincing steam, ice clarity, and the environmental richness that contextualizes a beverage shot. This guide provides specific prompt vocabulary for espresso and coffee drinks, tea, cold beverages, juices, cocktails, and the surfaces and props that make beverage imagery feel aspirational. You will learn how to describe liquid color and opacity, surface texture, condensation patterns, and the domestic or cafe environmental context that gives each drink its emotional register.

Espresso and Coffee Drink Fundamentals

Coffee drinks have highly specific visual signatures that vary by preparation method, and naming the drink type alone is insufficient to produce a convincing image. The most critical element for espresso-based drinks is crema — the golden-brown foam layer that sits on top of a freshly pulled espresso shot. Crema prompt vocabulary: 'freshly pulled double espresso in a small white demitasse cup, the crema on top of the coffee approximately 3-4mm thick, the crema surface in a rich warm caramel-brown with a slightly darker ring at the rim of the crema where it meets the cup wall, the crema surface showing the characteristic tiger-striping pattern of fine lighter and darker brown streaks radiating from the center, the crema surface slightly domed above the cup rim due to surface tension, a few very fine micro-bubbles visible at the crema surface, the crema color a warm mix of amber, caramel, and dark brown tones.' For a flat white or cappuccino with latte art: 'flat white in a 150ml ceramic cup, the latte art on the surface a classic rosette pattern poured in white steamed milk against the dark espresso-stained background, the rosette showing approximately seven leaf shapes arranged symmetrically, the milk foam approximately 5mm thick, the surface of the latte art still intact and fresh with sharp boundary between the white milk pattern and the brown coffee background, the milk foam surface showing a slight gloss from the steamed milk protein.' For a drip or pour-over coffee: 'pour-over coffee in a clear glass Chemex flask, the coffee a rich amber-brown in color, clear enough to see the Chemex funnel shape through the liquid in the upper portion, the liquid level approximately three-quarters of the Chemex capacity, a thin layer of bloom foam visible on the surface of the completed brew where the CO2 from fresh coffee has caused bubbling during the pour, the Chemex flask on a wooden cutting board with a wooden handle filter holder visible at the top.'

Steam, Condensation, and Surface Moisture

Steam and condensation are physically complex phenomena that AI models frequently render incorrectly — producing either an opaque white blob for steam or a completely dry glass for a cold beverage. Describing these atmospheric effects accurately is what elevates a beverage image from flat to photorealistic. For hot coffee steam: 'fresh hot coffee emitting a thin wisp of steam from the surface, the steam rising as a narrow transparent column approximately 3cm high, the steam in the lowest section near the liquid surface as a semi-transparent haze, becoming more defined and slightly denser at 1-2cm height, then gradually dispersing and becoming less visible toward the top of the steam column, the steam slightly offset to the right suggesting a very gentle air movement in the scene, the steam semi-transparent — the background visible through it at full opacity, the steam visible primarily because it refracts and scatters the light differently from the clear air around it.' For condensation on a cold glass: 'iced coffee in a clear glass, the exterior of the glass showing active condensation, the glass surface covered with water droplets ranging from tiny 0.5mm spherical droplets to larger 3-4mm flattened drops, the drops mostly spherical near the top of the glass transitioning to elongated tear-shaped drops lower down where they have begun to run, the condensation creating a frosted visual effect that slightly obscures the glass transparency, a few condensation rivulets running down the glass exterior where drops have merged and begun to flow, the condensation concentrated more heavily in the lower half of the glass where the drink is coldest.' For a milky condensation on a chai latte vessel: 'ceramic chai latte mug with a gentle visible steam rising from the surface, the outside of the ceramic mug warm to the touch implied by the absence of condensation (a warm cup does not condense moisture from the air), the ceramic surface dry and matte, the steam the only atmospheric effect, rising in gentle tendrils rather than a solid column.'

Glassware and Vessel Transparency

Beverage glassware is among the most optically complex objects in product photography because it must read as truly transparent while simultaneously revealing the liquid inside with correct color and opacity. The glass also refracts, reflects, and bends the scene behind it. For a clear drinking glass with layered beverage: 'tall clear glass containing an iced latte, the drink showing visible layers — a base of amber-colored espresso at the bottom, transitioning through a mid-section of caramel-colored mixed coffee and milk, topped with a layer of white cold-foamed milk approximately 3cm thick, the three layers partially mixed at their boundaries, the ice cubes visible through the clear glass walls — clear ice with internal fracture lines, cube faces slightly frosted at the surface where they contact air, the clear glass wall showing a curved specular highlight from the studio light on the right side, the background visible in a slightly distorted and color-shifted form through the glass.' For a dark glass vessel: 'cold brew coffee in a dark amber glass mason jar, the amber glass transmitting the dark coffee color as a deep warm brown, the jar lid a silver metal screw-top, ice visible through the amber glass as slightly lighter zones within the dark liquid, the jar exterior showing light condensation appropriate to a cold drink, the amber glass color adding a warm vintage quality to the dark coffee within.' For a pour moment: 'single-origin coffee being poured from a gooseneck kettle into a ceramic drip server, the thin pour of water visible as a narrow transparent stream approximately 5mm diameter, the stream slightly catching light as a thin bright line against the darker background, the pour entering the coffee filter at a controlled center point, a small amount of bloom foam visible at the coffee surface around the pour point where the hot water is causing fresh CO2 to release from the grounds.'

Tea, Juice, and Cold Beverage Vocabulary

Beyond coffee, beverage photography encompasses a diverse range of liquids each with their own characteristic visual properties. Tea has its own family of appearances: 'ceramic teapot on a wooden tray beside a small handled teacup, the teapot in a celadon green glaze with a bamboo handle, the teacup showing the tea inside as a warm amber-gold color for a medium-strength black tea, the tea surface in the cup showing a very slight ring of darker condensation at the cup wall and a faint transparent shimmer from the essential oils released during brewing, a thin slice of lemon visible on the rim of the cup, the tea approximately three-quarters filling the cup.' For a fruit smoothie or juice: 'freshly blended strawberry smoothie in a clear glass with a wide-bore compostable straw, the smoothie a rich magenta-pink opaque liquid, the glass showing the drink as completely opaque — no transparency — the vivid color saturated and even, the surface of the smoothie in the glass slightly domed from the blending, a few small air bubbles on the surface from the blending process, a fresh whole strawberry placed on the rim of the glass, the straw in dark green compostable PLA material.' For a sparkling water or soda: 'tall glass of sparkling water with lemon, the water transparent and clear, CO2 bubbles rising from three nucleation points on the interior glass surface in thin continuous columns of tiny spherical bubbles, the bubbles approximately 1mm diameter at the glass bottom growing to 2mm as they rise, the lemon slice floating at the surface with a few bubbles clinging to its skin, ice cubes below the lemon visible as clear crystal cubes with slight cloudiness at their centers.' For matcha: 'freshly whisked matcha in a traditional Japanese tea bowl (chawan), the matcha a vivid bright green color with a slight froth on the surface from the bamboo whisk whisking, the froth concentrated in the center of the bowl as a slightly paler zone of micro-bubbles, the sides of the bowl showing the characteristic streak marks from the bamboo chasen during whisking, the dark clay body of the chawan visible at the unglazed foot ring.'

Environmental Context and Prop Styling for Beverages

Beverage photography rarely shows a drink in complete isolation. The environmental context and prop styling communicate the emotional register — a morning ritual, an afternoon cafe break, a summer picnic, a late-night cocktail. Building this context into your prompt is what transforms a beverage product shot into a lifestyle image with purchase motivation. For a morning coffee ritual: 'morning coffee setup on a light oak kitchen surface, the hero object a ceramic mug of black pour-over coffee in a matte sage green glazed ceramic mug, placed beside an open paperback book face-down showing its spine, a small wooden coffee scoop resting across the top of an open glass jar of whole coffee beans, a small succulant in a terracotta pot in the right background slightly out of focus, morning light raking across the surface from the left at a low angle suggesting early morning, the overall color palette warm wood, soft green, and cream, the mood of a quiet personal morning ritual.' For a summer cold drink: 'tall iced tea on a weathered white-painted outdoor wooden table, the glass surrounded by a few scattered fresh mint leaves, a halved lemon showing its interior beside the glass, the whole scene in bright summer outdoor light with soft dappled shadows from a tree canopy above creating moving light patterns on the table surface, the background suggesting an outdoor garden or terrace, the mood of summer leisure.' For a third-wave coffee shop context: 'specialty coffee flat white in a small white porcelain cup on a marble cafe bar surface, the background showing a blurred cafe environment — warm dark wood shelving with coffee equipment, pendant lights creating warm bokeh circles at various depths, the cafe environment suggesting quality and craft, the cup and coffee the sharp focused element against the atmospheric blurred cafe depth of field.' For a cocktail: 'crystal-clear old fashioned cocktail in a classic rocks glass, the whiskey-based drink in a warm amber color, a large 2-inch square ice cube centered in the glass, an orange peel twist draped over the rim, a single Luxardo cherry on a cocktail pick resting across the rim, the glass on a dark polished wood bar surface showing a faint reflection of the glass below, a single warm spotlight from above creating a pool of warm light on the glass and surface, a dark atmospheric bar setting in the defocused background.'

Batch Beverage Content Workflows in Floniks

Beverage brands — whether coffee roasters, tea brands, juice companies, or cocktail mixers — need consistent visual content across multiple drinks and seasonal offerings. A coffee brand launching six single-origin coffees for a seasonal menu needs hero images of each drink (typically espresso, drip, and a milk-based drink) alongside lifestyle context shots — nine images per origin, fifty-four images total for a six-origin launch. Managing this manually would require days of prompt iteration. In the Floniks workflow editor, a shared photographic context node stores the brand's consistent visual identity: cup style and color, surface material, lighting setup, background character, and overall color grade. Six origin nodes feed into this shared context, each contributing the coffee-specific visual elements: the crema color and density for a particular roast, any unique preparation notes, the coffee's color when poured, and any accompanying garnish or presentation elements. Three branch nodes from each origin node produce the three drink styles (espresso, drip, milk-based) using the origin's characteristics as inputs. A final post-processing node applies a consistent film-emulation warm grade across all outputs. The entire fifty-four-image set runs in a single workflow execution. For seasonal drink menu updates, only the origin nodes need to change — the photographic context, branding, and image character remain constant. Cocktail brands can use the same architecture with spirit-specific nodes feeding into occasion-context branches (summer terrace, winter bar, celebration setting) producing a full seasonal content calendar from a single workflow configuration.

Step by step

  1. 1

    Describe crema or liquid surface texture explicitly for coffee drinks

    Crema and foam surfaces are where coffee images succeed or fail. Describe the thickness, color range, surface pattern (tiger-striping for espresso, rosette for latte art), and boundary characteristics. A detailed surface description prevents the model from rendering a flat brown circle as the drink surface.

  2. 2

    Describe steam as semi-transparent with a specific rise height and shape

    Steam rendered as an opaque white blob ruins a beverage shot. Describe steam as a narrow column with defined height, semi-transparent character, and slight directional offset from ambient air movement. The background should be visible through the steam.

  3. 3

    Use environmental context props to communicate the emotional register

    Name 3 to 5 specific props and their spatial relationship to the beverage. The prop selection communicates the occasion — morning ritual, cafe break, summer outdoor, evening cocktail — without needing to state the occasion explicitly. Each prop choice is a visual cue that adds narrative richness.

FAQ

Why does latte art in AI-generated images always look like a random swirl rather than a recognizable pattern?+

Latte art patterns like rosetttes, hearts, and tulips have specific geometric logic that AI models struggle to reproduce accurately. Describe the pattern with its structural logic: for a rosette, describe the number of leaf segments, their symmetrical arrangement, and the center line. For a heart, describe the pointed bottom and two rounded lobes. Also specify that the milk and coffee boundary should be sharp and well-defined. For commercial use where exact pattern accuracy is essential, generate a clean white foam surface and composite the latte art design in post-production.

How do I make ice in a glass look like real crystal-clear ice rather than white blobs?+

Specify the ice type explicitly: 'large clear ice cubes with slight internal fracture lines, the faces of the cubes slightly frosted where they contact air above the liquid, the submerged portions of the cubes completely transparent, the cubes showing slight rounding at the corners from melting, each cube casting a slightly blue-tinted shadow through the liquid behind it.' Clear ice has internal structure and different optical behavior at the waterline. Mentioning 'crystal-clear ice' and describing the fracture lines and air-contact frosting are the key cues.

Related guides

Build it on Floniks

Image, video, digital humans, and reusable workflows on one canvas. Sign up gets you starter credits — no card required.

Explore Floniks