Tao
Tao

Doubao Text-to-Image Prompts

Doubao Text-to-Image Prompts

This article introduces a carefully curated collection of Doubao text-to-image prompt templates to help you quickly generate high-quality, stylistically diverse images. These templates cover a wide range of artistic styles and scenes, from cozy and healing to minimalist art, from traditional ink wash to modern design, all of which can be personalized through simple adjustments. We hope this article helps you quickly generate the images you want.

Perfect for situations requiring precise control of various image elements, rich in detail, and ideal for complex scenes or specific artistic styles.

shell

Main Text: [Core vocabulary/concept]
Main Text Style: [Font type] + [Visual effect] + [Color/texture] + [Special details]
Auxiliary Text: [Supplementary words/explanation/symbols]
Auxiliary Text Style: [Style that contrasts with or complements the main text]
Core Art Style/Medium: [Specific art style] + [Creative medium]
Visual Techniques/Effects: [Focus treatment] + [Lighting effects] + [Special visual elements] + [Texture representation]
Main Scene Subject/Focus: [Specific scene/object related to the theme word]
Scene Background/Environment: [Environment description] + [Atmosphere elements]
Embellishing Elements/Details: [Small details enhancing the theme] + [Texture/dynamic elements]
Overall Mood/Feeling: [3-5 emotional/atmospheric adjectives]
Aspect Ratio: [Dimension ratio, such as 16:9, 1:1, 9:16, etc.]

Great for quick creation, emphasizing creativity and overall atmosphere, concise and efficient.

shell

Main text "[core vocabulary]", [creative expression form, such as "constructed from which elements" or "how to integrate with the image"];
Auxiliary small text "[supplementary text]", [concise style description];
[Scene description: brief description of character/object, action, environment that resonates with the main text];
[Background environment: brief description, 2-3 key elements];
[Embellishing elements: list 3-5 specific items];
[Overall artistic style description: art style + color characteristics + emotional expression];
Ratio "[dimension ratio]"

shell

Main Text: Warm
Main Text Style: Soft, rounded font, with fuzzy texture like wool or soft light effect, warm orange/yellow hue, emitting a gentle glow.
Auxiliary Text: "gmd, cozy"
Auxiliary Text Style: Simple white sans-serif font.
Core Art Style/Medium: Cozy, healing illustration style, slightly Ghibli-inspired.
Visual Techniques/Effects: Soft focus, background bokeh lights, warm ambient lighting.
Main Scene Subject/Focus: A steaming mug of tea/coffee held by hands wearing knitted mittens.
Scene Background/Environment: Cozy room interior with a fireplace or a window showing gentle snowfall outside.
Embellishing Elements/Details: Rising steam from the mug, soft reflections on surfaces.
Overall Mood/Feeling: Comfortable, Inviting, Gentle, Heartwarming.
Aspect Ratio: 4:3

shell

Main Text: Tranquil
Main Text Style: Soft, flowing script, semi-transparent like moonlight on water, cool blue/silver tones.
Auxiliary Text: "n. tranquility, quietness"
Auxiliary Text Style: Very subtle, almost faded.
Core Art Style/Medium: Dreamlike digital painting, soft brushstrokes.
Visual Techniques/Effects: Soft focus, gentle moonlight, reflections on water, fireflies or glowing plankton.
Main Scene Subject/Focus: A small wooden boat drifting on a perfectly calm lake under a full moon.
Scene Background/Environment: Starry night sky reflected in the water, distant misty mountains or forest edge.
Embellishing Elements/Details: Ripples from the boat, glowing fireflies.
Overall Mood/Feeling: Peaceful, Serene, Calm, Quiet, Ethereal.
Aspect Ratio: 16:9

shell

Main Text: Ink
Main Text Style: Calligraphy style, appearing as if actively dissolving or spreading like ink in water, black and grey tones.
Auxiliary Text: "n. ink"
Auxiliary Text Style: Simple, traditional font, small.
Core Art Style/Medium: Abstract ink wash painting style - digital simulation, Minimalism.
Visual Techniques/Effects: Ink bleed/diffusion effect, high contrast - black ink on white/rice paper texture, dynamic splatters.
Main Scene Subject/Focus: The character "墨" itself forming abstract shapes or landscapes as it spreads, could suggest a mountain range or dragon silhouette within the ink.
Scene Background/Environment: Textured paper background like Xuan paper.
Embellishing Elements/Details: Subtle paper texture, varying ink density.
Overall Mood/Feeling: Artistic, Fluid, Expressive, Minimalist, Traditional yet dynamic.
Aspect Ratio: 9:16 (vertical composition suitable for calligraphy/ink spread)

shell

Main Text: Against the current
Main Text Style: Text made of shimmering, determined-looking fish or energy forms, swimming against a powerful, visually represented current - river of flowing time, data streams, or abstract energy.
Auxiliary Text: "v. swim upstream, go against the current"
Auxiliary Text Style: Trailing behind the text-forms like a wake.
Core Art Style/Medium: Stylized illustration, Dynamic digital painting.
Visual Techniques/Effects: Strong sense of motion in the current, splashes and resistance around the text-forms, dramatic lighting highlighting the struggle.
Main Scene Subject/Focus: The text-fish battling the current in a river made of liquid starlight, flowing code, or melting clocks.
Scene Background/Environment: Surreal 'river' environment, banks could be made of crystal, cloud, or crumbling ruins.
Embellishing Elements/Details: Water/energy spray, determined 'expressions' on the text-forms.
Overall Mood/Feeling: Determined, Struggling, Defiant, Resilient, Powerful resistance.
Aspect Ratio: 9:16 (vertical composition emphasizing the struggle against the current)

shell

Main Text: Whisper
Main Text Style: Text formed from ethereal, swirling smoke, faint sound wave patterns, or heat haze, drifting directly towards or curling around the ear of a depicted character. Letters are semi-transparent and indistinct.
Auxiliary Text: "n. whisper"
Auxiliary Text Style: Barely audible, looks like faint echoes near the main text.
Core Art Style/Medium: Atmospheric digital painting, Psychological portraiture.
Visual Techniques/Effects: Soft focus on background, Sharp focus on the character's reaction and the 'whisper' text, subtle particle effects within the smoke/waves, Lighting highlighting the ear/side of the face.
Main Scene Subject/Focus: A close-up on a character's face - expression: intrigue, fear, confusion, whisper-text physically interacting with their ear or temple.
Scene Background/Environment: Dark, ambiguous, suggesting isolation or intimacy.
Embellishing Elements/Details: Character's subtle expression, Texture of the smoke/wave.
Overall Mood/Feeling: Secretive, Intimate, Influential, Potentially insidious or guiding, Ambiguous.
Aspect Ratio: 9:16 (vertical composition focusing on character interaction)

shell

Main Text: Harmony
Main Text Style: Letters formed by dense clusters of tiny colored dots, seamlessly blending with the surroundings.
Auxiliary Text: None
Auxiliary Text Style: None
Core Art Style/Medium: Pointillism, Stipple Art - gentle style.
Visual Techniques/Effects: Colors blend optically through juxtaposed dots, No harsh outlines, Granular texture.
Main Scene Subject/Focus: A serene landscape - gentle hills, calm water - or a peaceful portrait.
Composition Idea: The area of the text "和谐" is formed by denser dots or a subtle color variation, becoming part of the overall pointillist texture, embodying the sense of blending and unity.
Overall Mood/Feeling: Harmonious, Blended, Peaceful, Unified, Gentle texture.
Aspect Ratio: 16:9

shell

Main Text: Smile
Main Text Style: Friendly, rounded chalk font written on a blackboard background.
Auxiliary Text: (a few simple chalk drawing small stars)Auxiliary Text Style: Simple chalk drawing style.
Core Art Style/Medium: Chalkboard Art, Hand-drawn lettering.
Visual Techniques/Effects: Chalk texture and slight dustiness, Dark blackboard background, Simple lines.
Main Scene Subject/Focus: Chalk text and its decorations.
Composition Idea: The text "smile" itself conveys smiling - simple smiley faces drawn inside loops (like the 口 radical), or the entire text follows a gentle upward curve like a smile. Surrounds can be adorned with simple chalk flowers or stars.
Overall Mood/Feeling: Happy, Cheerful, Simple, Endearing, Ephemeral.
Aspect Ratio: 4:3

shell

Main Text: Shelter
Main Text Style: Letters constructed from moss, small rocks, or driftwood, forming parts of a miniature landscape.
Auxiliary Text: (a small house icon) 🏠
Auxiliary Text Style: Also built from miniature natural materials.
Core Art Style/Medium: Miniature world photography/illustration, Terrarium craft.
Visual Techniques/Effects: Intricate details, Gloss and reflection of the glass container, Shallow depth of field emphasizing miniature scale.
Main Scene Subject/Focus: The miniature landscape inside the glass terrarium.
Composition Idea: The letters of "庇护所" form small hills, caves, or tree-like structures within the terrarium, providing 'shelter' for tiny miniature figures or animal models resting beneath arches or inside loops.
Overall Mood/Feeling: Sheltered, Safe, Cozy, Miniature world, Contained nature.
Aspect Ratio: 1:1 or vertical ratio

shell

Main Text: Path
Main Text Style: Formed by a single, continuous, elegant line.
Auxiliary Text: (a simple arrow symbol)Auxiliary Text Style: Also made of simple lines, indicating direction.
Core Art Style/Medium: Minimalist Line Art, Elegant contour drawing.
Visual Techniques/Effects: Clean lines, Ample white space, Minimal color - black/white or monochrome plus one accent color.
Main Scene Subject/Focus: The line itself and the forms it creates.
Composition Idea: A single line fluidly forms the characters "路径" while simultaneously tracing a path winding through simple abstract shapes representing hills or stars.
Overall Mood/Feeling: Simple, Elegant, Clear direction, Journey, Understated.
Aspect Ratio: 16:9 or 1:1

shell

Main Text: Stream
Main Text Style: Letters formed by arranging smooth, naturally colored river stones, pebbles, and perhaps some blue/green sea glass.
Auxiliary Text: (a few small moss)
Auxiliary Text Style: Naturally scattered beside the text.
Core Art Style/Medium: Natural material mosaic art, Miniature Land art.
Visual Techniques/Effects: Emphasis on the natural texture and shape of the stones, Shallow depth of field, Natural lighting.
Main Scene Subject/Focus: The text stream formed by pebbles.
Composition Idea: The text "溪流" itself forms a winding path made of pebbles, mimicking a stream flowing across sand or moss, with the arrangement following a gentle curve.
Overall Mood/Feeling: Natural, Flowing, Clear, Textured, Peaceful, Handcrafted.
Aspect Ratio: 1:1

shell

Main Text: Melody
Main Text Style: Formed by a single, continuous, flowing undulating line that visually mimics a beautiful, gentle melody's contour or an abstract, soft soundwave pattern.
Auxiliary Text: (a few small eighth note symbols) ♪
Auxiliary Text Style: Also made of simple lines, dotted near the main line.
Core Art Style/Medium: Abstract Line Art, Minimalist visualization.
Visual Techniques/Effects: Line's fluidity and rhythm, Possible slight glow or color gradient along the line, Minimal background focusing attention on the line.
Main Scene Subject/Focus: The line forming the text and suggesting melody.
Composition Idea: The core of the composition is this single line, which both writes the text and directly expresses the flow and beauty of 'melody' through its undulations and extensions.
Overall Mood/Feeling: Melodious, Flowing, Graceful, Harmonious, Continuous movement.
Aspect Ratio: 21:9 (wide format suitable for line extension)

shell

Main Text: Spring Blossoms
Main Text Style: Light pink and white text with a gentle glow effect, formed by floating cherry blossom petals suspended naturally in the air.
Auxiliary Text: "Spring. / The gentle season of renewal"
Auxiliary Text Style: Light grey handwritten font, vertically arranged in the lower right corner of the image.
Core Art Style/Medium: Japanese-inspired watercolor illustration
Visual Techniques/Effects: Shallow depth of field, gentle side lighting (simulating morning sunlight), dynamic sense of wind-blown petals, focus on the text.
Main Scene Subject/Focus: The text "Spring Blossoms" formed by cherry blossom petals.
Scene Background/Environment: A blurred corner of a vibrant spring park with fresh green grass and distant cherry blossom tree silhouettes.
Embellishing Elements/Details: A few individual falling petals, tiny light spots in the air.
Overall Mood/Feeling: Warm, Hopeful, Fresh, Romantic.
Aspect Ratio: 16:9

shell

Main Text: "Home-body", shaped like a house with windows emitting warm light from within.
Auxiliary small text: "My WiFi coverage area is my kingdom", in pixel game interface font.
Scene description: A person comfortably curled up in a huge, fully-equipped (bed, computer, snack rack, gaming console) snail shell or castle, isolated from the outside world.
Background environment: The external world seen through windows is blurred or stylized (showing rain or nighttime).
Embellishing elements: Router, cat, potted plant, bookshelf.
Overall artistic style: Cozy healing illustration style, rich in detail, soft colors, emphasizing safety and comfort.
Ratio "4:3"

shell

Main Text: "Coffee AM, Wine PM", with half of the text featuring morning sunlight coffee cup patterns, half featuring night sky wine glass/skincare bottle patterns.
Auxiliary small text: "Energize by day, unwind by night", in modern minimalist sans-serif font.
Scene description: Split screen composition - left side shows a silhouette holding coffee overlooking a city CBD at sunrise; right side shows a silhouette holding a wine glass or skincare product at a vanity table by moonlight.
Background environment: Left side shows modern urban daytime scene, right side shows cozy bedroom/bar nighttime setting.
Embellishing elements: Computer/documents on left side, aromatherapy diffuser/books/skincare products on right side.
Overall artistic style: Digital painting with contrasting styles - half bright and energetic, half soft and relaxing, emphasizing lifestyle balance.
Ratio "3:4"

shell

Main Text: "citywalk", in map route style font with location pin 📌.
Auxiliary small text: "Measuring cities one step at a time, finding surprises around every corner", in vintage street sign or graffiti font.
Scene description: Bird's-eye view of a figure leisurely walking on a detailed city street map marked with coffee shops, bookstores, specialty stores, and graffiti walls, following an interesting winding route.
Background environment: Delicately hand-drawn city map with various landmarks.
Embellishing elements: Magnifying glass icon focusing on an interesting corner detail, scattered Polaroid photos.
Overall artistic style: Fresh map illustration or journal-style collage art, rich in color, full of details, inspiring exploration.
Ratio "3:4"

shell

Main Text: "Dopamine Dressing", in rainbow-colored, high-saturation Pop Art font.
Auxiliary small text: "Wear your happiness!", in eye-catching uppercase slogan font.
Scene description: A person wearing bold, bright, color-blocked clothing confidently walking on a street with monochromatic or minimalist background, creating strong visual contrast, surrounded by colorful auras or geometric shapes.
Background environment: Minimalist city architecture or solid color background wall.
Embellishing elements: Exaggerated accessories (colorful sunglasses, oversized earrings, unusually shaped bags).
Overall artistic style: Fashion street photography or trendy illustration, emphasizing color impact and self-expression.
Ratio "3:4"

shell

Main Text: "Extreme Makeover", in dynamic font with speed lines, half old and half new.
Auxiliary small text: "So dramatic even your mother won't recognize it!", in emphatic exclamation font.
Scene description: A room/object/person divided by a split line (zipper or tear effect), clearly showing the dramatic contrast between before and after, with tool symbols like drills, brushes, and scissors in the middle.
Background environment: "Before" side shows ordinary or worn background, "After" side shows fresh, design-forward background.
Embellishing elements: Paint bucket, measuring tape, fabric swatches, design sketches.
Overall artistic style: High-contrast visual design, combining realistic photo collage or dramatic illustration to highlight the stunning transformation effect.
Ratio "3:4"

shell

Main Text: "Check-in", in font shaped like map location pins 📍 or camera shutter.
Auxiliary small text: "Travel for what you love, stay for what you discover", in travel journal or handwritten font.
Scene description: A smartphone screen occupies most of the image, displaying a popular landmark/restaurant/exhibition being photographed, with part of the actual scene visible around the phone, creating a picture-in-picture effect.
Background environment: Popular check-in location as background (famous building, art installation, scenic spot, unique store).
Embellishing elements: Polaroid photos, marked route map, coffee cup/food photos, tickets/boarding passes.
Overall artistic style: Travel photography or lifestyle documentation style, emphasizing immediacy and shareability, with aesthetically pleasing composition and attractive colors.
Ratio "3:4"

shell

Main Text: "I cannot possibly do this!", in dramatic calligraphy font with flowing ink.
Auxiliary small text: "Your Majesty!", in small desperate annotation font.
Scene description: Close-up of Zhen Huan (Sun Li's character) with emotional, grief-stricken or desperate expression, tears in eyes, wearing elaborate but slightly disheveled Qing Dynasty royal attire.
Background environment: Opulent but oppressive imperial palace interior, featuring palace walls and ornate window frames.
Embellishing elements: Intricate but cold headdress (with kingfisher feather ornaments), loose strands of hair, power struggle symbols (chess pieces, imperial documents).
Overall artistic style: Fine-brush portrait or dramatically theatrical illustration emphasizing facial expression and gaze, colors can be luxurious but atmosphere remains heavy.
Ratio "3:4"

shell

Main Text: "Roman Holiday", in vintage movie poster font.
Auxiliary small text: "Classics never fade", in elegant typewriter font.
Scene description: Princess Ann (Audrey Hepburn style) wearing white blouse and full skirt, riding with Joe (Gregory Peck style) on a Vespa motorcycle, joyfully cruising past iconic Roman landmarks, with radiant smiles.
Background environment: Ancient Roman ruins, such as the Colosseum or Spanish Steps.
Embellishing elements: Vintage Vespa motorcycle, flowing silk scarf.
Overall artistic style: Classic black and white film photography or color illustration with retro filter, capturing moments of freedom, romance and elegance.
Ratio "16:9"

shell

Main Text: "I'm the king of the world!", in free-spirited, powerful script font.
Auxiliary small text: "Jack & Rose", in elegant vintage decorative font.
Scene description: Jack (Leonardo DiCaprio style) standing at the bow of the Titanic with arms outstretched, Rose (Kate Winslet style) embracing him from behind, both facing the ocean and wind.
Background environment: Vast endless ocean and sky, magnificent sunset or sunrise.
Embellishing elements: Massive ship bow railing, flying seagulls, billowing clothing edges.
Overall artistic style: Epic oil painting style or cinematic digital painting, expansive scene, rich colors, emphasizing freedom, romance and youthful passion.
Ratio "16:9"

shell

Main Text: "No obsession, no life", in Beijing opera script font integrated with costume patterns.
Auxiliary small text: "A lifetime promised, a year, a month, or a day short is not a lifetime!", in resolute brush calligraphy.
Scene description: Close-up of Cheng Dieyi (Leslie Cheung's character) in classic Yu Ji makeup, with melancholic yet determined gaze, wearing elaborate face paint, with blurred stage or mirror background.
Background environment: Old-time theater backstage or stage.
Embellishing elements: Edge of a phoenix crown headdress, intricate embroidery on costumes, sword symbolizing fate.
Overall artistic style: Period-styled oil painting or detailed brush painting illustration, rich colors emphasizing emotional intensity and tragic themes.
Ratio "3:4"

Doubao’s text-to-image capabilities in this update are truly impressive, far exceeding expectations. The range of artistic styles it can now handle has significantly expanded, with a substantial leap in aesthetic quality and a marked improvement in understanding and executing prompts. Chinese text generation stability has also greatly improved—though there are still some limitations with small fonts and complex multi-text scenes, the overall stability represents a comprehensive upgrade.

However, there are still areas for improvement. Currently, Doubao’s “comfort zone” primarily centers on practical and business-oriented styles, with certain specific styles (like cyberpunk) lacking sufficient variation and texture. This likely stems from training data preferences, but from an overall strategic perspective, this practical, mass-market approach is undoubtedly the right direction.