Stable Diffusion 3.5 Prompt Guide

1. Logo Concept Generation Prompt

You are a top-tier logo designer with 20 years of experience, having designed instantly recognizable and deeply meaningful logos for globally renowned brands.

Brand Name: [Your Brand Name]
Industry: [Your Industry]
Brand Personality: [Description]
Target Audience: [Description]
Admired Visual Identities: [List 3]
Disliked Visual Identities: [List 3]
Preferred Style: [e.g., minimalist, bold, geometric, organic, vintage, futuristic]

Generate 5 completely different logo concepts for my brand.

For each concept provide:

- Core visual concept and symbolism
- Shape language and why it suits the brand
- Font direction recommendations
- First emotional trigger
- Why it suits the target audience
- How it would look on business cards, app icons, and billboards
- Why it's timeless rather than trendy

Then tell me which one you would choose if this were your brand and why.

2. Brand Identity Foundation Prompt

You are a top-tier brand strategist who builds brand identities for Fortune 500 companies and startups that later raise millions in funding.

Business Name: [Your Business Name]
Business Description: [One sentence]
Target Audience: [Detailed description]
Competitors: [List 3-5]
Feelings to evoke: [e.g., trust, excitement, luxury, approachability, power]
Words to associate: [List 5-10]
Words not to associate: [List 5-10]

Establish a complete brand identity foundation before designing any visual elements.

Provide me with:

- Brand archetype and why it's a perfect fit
- 5 specific human characteristics describing the brand personality
- Brand tone guide with examples
- Core brand promise (one sentence)
- 3 emotional levels the brand should trigger
- Fundamental difference from competitors
- The one keyword that defines the brand

3. Color Scheme Prompt

You are a color psychology expert and brand designer who deeply understands how colors trigger emotions, build trust, and drive purchasing decisions.

Brand Name: [Your Brand Name]
Industry: [Your Industry]
Target Audience: [Age, gender, income, lifestyle]
Primary emotion to evoke: [e.g., trust, energy, luxury, calm, excitement]
Top 3 competitor colors: [List]
Liked colors: [List]
Disliked colors: [List]

Build a complete brand color palette for me.

Provide me with:

- Primary color with HEX code and psychological explanation
- Two secondary colors with HEX codes
- One accent color for CTAs and highlights
- One neutral color for backgrounds and text
- How each color affects the target audience
- Differentiation from competitors
- Application examples on websites, social media, and packaging
- Color combinations to never use and why

4. Typography Direction Prompt

You are a typography expert and brand designer who deeply understands how fonts convey personality, build credibility, and achieve instant brand recognition.

Brand Name: [Your Brand Name]
Brand Personality: [5 words]
Industry: [Your Industry]
Target Audience: [Description]
Feelings fonts should evoke: [e.g., authority, friendly, innovative, elegant, energy]
Liked brand fonts: [List 3]

Build a complete typography system for me.

Provide me with:

- Primary display font name for headings and why it's perfect
- Secondary font for long text
- Accent font for quotes or emphasis
- Precise font size hierarchy for headings, subheadings, body text, and captions
- Letter spacing and line height recommendations
- Font pairing methodology
- Free alternatives if budget is limited
- Font mistakes to avoid in your industry

5. Complete Brand Identity Package Prompt

You are a top-tier creative director at a brand agency, delivering complete brand identity systems that cover every touchpoint.

Business Name: [Your Business Name]
Business Description: [One sentence]
Target Audience: [Detailed description]
Brand Personality: [5 words]
Industry: [Your Industry]
Competitors: [List 3]
Design tool budget: [Free or paid]
Timeline: [Time you need]

Deliver my complete brand identity system in one response.

Include all elements:

- Brand strategy foundation, archetype, personality, promise, and positioning
- Logo concepts with 3 variations
- Complete color palette with HEX codes and usage rules
- Typography system with names, sizes, and hierarchy
- Visual direction guidelines
- Brand tone guide and tagline options
- Social media visual templates
- 3 core brand rules to never break

Deliver everything as a structured brand guide that any designer, developer, or AI tool can fully understand your brand in 10 minutes.

Generate a 3:4 vertical 9-grid poster suitable for publishing on Xiaohongshu, with an overall layout of 3 columns × 3 rows. The boundaries of the nine grids are clear, making it easy to directly cut into 9 single images for later publishing. The overall style is clean, premium, and unified, suitable for female-oriented healthy lifestyle content, possessing the vibe of a viral Xiaohongshu cover. Image requirements: clear information layout, large text, strong readability, comfortable white space, gentle and healing color palette.

Overall visual style:
Cream white, light beige, light oat color, and light caramel color as the main color tones, paired with a small amount of dark brown text. Ins style, healing sense, sleep therapy theme, minimalist layout, light skeuomorphic illustration embellishments. Elements such as pillows, moons, stars, hot milk, aromatherapy, books, eye masks, curtains, and beds can be added. The overall look should be like a professional new media design graphic, with neat fonts, suitable for a knowledge-based popular science Xiaohongshu 9-grid.

Layout requirements:
The entire image must be a standard 9-grid composition, and each grid can stand alone as an independent image after being cut.
The content of each grid should be completely centered; do not place titles or body text near the dividing lines.
Keep obvious gaps or thin borders between each grid to ensure that reading is not affected after cropping.
All text must use Chinese, be clear and readable, no garbled characters, no English.
Each grid should look like an independent Xiaohongshu image-and-text card, but the visual style must remain unified.
The image should be exquisite, realistic, and natural, without a cheap marketing feel, and not overly flashy.

Specific content of the 9-grid:

Grid 1 (Cover)
Main title: 8 tips to make you fall asleep instantly
Subtitle: Insomniacs and night owls must save this
The cover visuals should be the most eye-catching, suitable for the first image. Add healing sleep elements such as soft beds, moons, pillows, and eye masks. The title should be prominent with a premium layout.

Grid 2
Title: 1. Don't play with your phone 1 hour before bed
Body text: Blue light makes the brain more awake; the more you scroll, the harder it is to fall asleep.
Image elements: Mobile phone, moon, small illustration of a sleepy expression

Grid 3
Title: 2. Dim the lights before bed
Body text: A warm light environment can help the body enter a "ready to sleep" state.
Image elements: Bedside lamp, warm yellow light, curtains

Grid 4
Title: 3. Don't keep the room temperature too high
Body text: Keeping it a bit cooler makes it easier to fall asleep quickly.
Image elements: Air conditioner, thermometer, quilt

Grid 5
Title: 4. Don't drink strong tea or coffee at night
Body text: Caffeine delays sleepiness, making you lie in bed for a long time unable to sleep.
Image elements: Coffee cup, teacup, prohibition sign

Grid 6
Title: 5. Take a hot shower before bed
Body text: It can relax the body and help you fall asleep faster.
Image elements: Bathroom steam, towel, hot water

Grid 7
Title: 6. Write it down if your brain won't stop
Body text: Writing down your worries and to-do lists makes it easier for your brain to relax.
Image elements: Notebook, fountain pen, small desk lamp

Grid 8
Title: 7. Fix your bedtime
Body text: Going to bed at about the same time every day will make your biological clock increasingly stable.
Image elements: Clock, moon, bed

Grid 9
Title: 8. Try deep breathing relaxation
Body text: Inhale for 4 seconds, hold for 4 seconds, exhale for 6 seconds, and sleepiness will gradually come.
Bottom small text: Save this set and try it tonight
Image elements: Breathing lines, person with closed eyes, stars

Image quality requirements:
High definition, premium layout, magazine feel, realistically publishable, new media operation aesthetics, Xiaohongshu viral image-and-text style, neat text layout, suitable for direct image cutting.

Transform the uploaded image into cinematic 3-frame sequential film stills (horizontal frames stacked vertically), full bleed edge-to-edge. Each frame should show a different moment from the same scene, with clear progression. Vary the composition, camera angle, and distances to create a sense of movement and storytelling. Use a cinematic, {argument name="color tone" default="cooler-toned"}, high-contrast, deep-space blacks film with a natural color grade. Add subtle film grain, slight motion blur, and natural imperfections to emulate analog photography. Keep the composition candid and emotionally grounded, with a sense of movement and quiet storytelling. Overall aesthetic: cinematic, nostalgic, and organic, like raw film stills.

Ultra-clean automotive poster featuring the exact same car as the photo that will be provided later. The AI must replicate the car from the uploaded photo with identical body shape, proportions, stance, color, trims, wheels, and all visible exterior details.
The car is presented in a front three-quarter angle facing right, matching the perspective of the original reference layout, but now depicted in a subtle {argument name="action" default="drifting action"}. The drift is expressed through realistic weight transfer, slight body lift, controlled smoke plumes from the rear tires, and faint curved tire marks behind the vehicle, without distorting the original car’s geometry.
Headlights follow the exact style from the reference photo of the car, with optional warm fog lights glowing if the provided car has them. All decals, emblems, plates, and window tints must match the car from the uploaded photo.
The car drifts on a glossy white reflective studio-like floor that maintains soft reflections and realistic shadows, enhanced with light drift skid reflections and directional smudges.
Background remains a clean white-to-light-gray gradient with a giant semi-transparent bold typography of the car model name (auto-extracted from the uploaded photo) vertically dominating the background.
At the very top: clean branding text “{argument name="brand name" default="CAR COMPANY NAME"}” (or the brand detected from the uploaded car photo). Under it, spaced-out stylized tracking text containing the same brand and model name.
Below the car: centered title of the exact model name from the uploaded photo.
Under that, a short descriptive paragraph about the car’s character (efficiency, style, reliability).
Bottom section shows a clean grid layout of specifications. If real specs are known from the detected car model, generate accurate values; if not, generate placeholders in the same layout style (4 columns: horsepower, 0–100 km/h, top speed, engine displacement/fuel type).
Entire poster is minimalist, editorial, high-key studio lighting with ultra-sharp reflections, crisp shadows, modern typography, and 4K believability, blending clean design with dynamic drifting energy, Ratio 9:16

analyze this photo and give me a detailed JSON prompt that recreates it. break down the color grading and every exact color in the photo

(use Opus, not Sonnet. Opus has stronger visual analysis and writes more detailed JSON)

paste that JSON into ChatGPT
upload your product image and prompt:
using this JSON as reference, generate a person holding my product
save that generated photo as your character reference

attach it to every future generation for facial consistency

you now have a consistent UGC model that works across any product

the JSON controls the lighting and color grading. GPT image-2 handles the character. you control the product placement.

the #1 tell on AI photos is flat colors and a grainy look. this method removes both.
5 minutes to set up. unlimited variations after.

Old money Hamptons editorial, tall blonde woman late 20s, serene elegant expression, wearing cream cashmere cable sweater, pleated beige tennis skirt, pearl earrings, Hermès silk scarf, leather flats, Slim Aarons photography style, medium format film photography, sitting on a white wooden porch of a Cape Cod house, golden hour light, ocean in the background

Create a hyper-detailed comedic Japanese arcade fighting game screenshot styled like a versus battle scene, using a real-world photo aesthetic with game UI overlaid on top. The scene shows an intense mock battle between two groups of theme-park fans competing for the front row at an outdoor show plaza in Tokyo DisneySea. Use a wide 16:9 composition. In the background, clearly show Mediterranean Harbor and Mount Prometheus under bright daytime skies, with the waterfront and DisneySea architecture visible. In the foreground, show exactly 10 young adult people in winter casual clothing, split into 2 opposing teams of 5, physically leaning, grabbing, reaching, and shoving in a tug-of-war-like scrum over position, with exaggerated competitive body language and frozen action as if in a fighting game. Faces should be anonymized with soft blurred blocks. Add floating character labels above each person with levels and names in Japanese. The overall tone is absurdly realistic, like a real candid photo transformed into a polished arcade game battle screen.

Add a full Japanese fighting-game HUD with glossy blue-versus-red interface styling. At the very top, place a center stage title bar reading "東京ディズニーシー ミッキー広場 ショー最前列バトル" and a large timer in the middle reading "TIME 89". In the top left, add a blue team header "PLAYER1" and team name "最前列ガチ勢A". In the top right, add a red team header "RIVAL" and team name "ライバルグループB". On the left side, stack exactly 5 blue player status panels with portraits, level, Japanese class-like nicknames, HP, SP, and BURST meters. The 5 left-side labels are: "Lv.25 ガチ勢リーダー ユウキ", "Lv.24 筋肉マン タケシ", "Lv.23 眼鏡オタク シンジ", "Lv.23 開角心MAX ケント", "Lv.22 サポート要員 リョウ". On the right side, stack exactly 5 red rival status panels with the labels: "Lv.27 ライバルリーダー ダイキ", "Lv.26 パワフル代表 マサル", "Lv.24 戦略家 コウジ", "Lv.23 熱血漢 リク", "Lv.22 サポート女子 サキ". Each panel should include numeric HP and SP values and segmented BURST gauges, styled like a Japanese arcade RPG-fighter interface.

Place exactly 10 in-battle nameplates above the fighters in the center scene, color-coded blue for the left team and red for the right team. The 10 labels are: "Lv.24 タケシ", "Lv.25 ユウキ", "Lv.23 シンジ", "Lv.23 ケント", "Lv.22 リョウ", "Lv.27 ダイキ", "Lv.26 マサル", "Lv.23 リク", "Lv.22 サキ", "Lv.22 ミサキ".

At the lower left, add a skill menu titled "スキル" listing exactly 5 skills with SP costs: "ダッシュ突撃 SP 20", "肩押し強奪 SP 25", "荷物で場所確保 SP 15", "ロープくぐり SP 10", "本気の根性 SP 50". Beneath that, add a dark description box explaining the highlighted skill "本気の根性" with the Japanese text: "気合で相手を威圧し、どかす! 一定時間、相手が怯みやすくなる! (バーストゲージを大きく消費する) 効果時間:10秒".

At the bottom center, add an item menu titled "アイテム" with exactly 5 item slots showing icons and counts: a water bottle "x3", a folded purple towel "x2", a blue drawstring bag "x1", a gray backpack "x1", and a boxed meal "x2". At the lower right, add a quest panel titled "クエスト" with the mission text "ショー開始までに最前列を死守しろ!" and condition text "条件:ライバルグループを全員後ろに押し戻せ!" and countdown text "ショー開始まで:02:30". Beside it, add a mini-map titled "ミッキー広場MAP" showing red and blue dots for both teams in the plaza. Along the very bottom edge, include small controller prompts in Japanese for actions such as skill use, item use, grab/push, and dash.

Use dramatic, saturated lighting, crisp detail, realistic clothing folds, authentic plaza stone pavement, and a high-end Japanese game screenshot look. The image should feel like a ridiculous but believable crossover between a real Tokyo DisneySea crowd photo and a competitive arcade battle game interface.

Create a 4:5 vertical social poster in ultra high resolution, 8K print quality sharpness. Use the {argument name="car model" default="BMW car"} from the reference image as the main subject and use the background structure/composition from the reference image, but transform it into a BMW themed design. Replace all black tones with a flat {argument name="background color" default="high-saturation BMW blue"} background. Keep the same layout, spacing, visual balance, and poster composition from the reference image. Background should use a smooth gradient from slightly lighter electric blue at the top to deep navy blue at the bottom. Add subtle grain texture (2 to 3%) and faint rectangular overlays (2 to 4% opacity). Keep it clean, graphic, premium, and non-realistic. Add a soft contact shadow under the car. Use the same BMW from the reference image, changing only the {argument name="paint finish" default="matte frozen blue"} or deep metallic navy. Keep the original body shape, wheels, stance, and design details from the reference image. Show the car in a rear 3/4 perspective matching the reference image angle exactly. Use a slightly elevated camera angle. Position the car slightly right of center. Include visible carbon roof, aggressive rear diffuser, sharp controlled reflections, and subtle brake details. Keep composition identical to the reference image: Top: branding Middle: giant type Center: car overlapping text Bottom: editorial block and specs Typography: Primary text: “BMW” Ultra condensed bold sans serif, tall vertical scaling like the reference poster. Color deep navy or near black. Static text with no distortion. Acts as structural backdrop. Secondary header: “BMW M4 G82” Thin font with wide tracking. Logo area: BMW roundel centered above. Editorial block: Headline: “BMW — Where Driving Becomes Instinct” Body copy focused on: driver connection control performance precision Use the same boxed editorial layout as the reference image. Background faded text: “M4” large scale with 3 to 5% opacity behind the box. Bottom left: “ M4 G82” Bottom right specs: 405 kW / 550 PS 3.4 s 307 km/h Lighting should be clean studio lighting with sharp but controlled highlights. Color grading should use deep blues, high contrast, clean blacks. Camera lens: 50mm, slightly elevated rear 3/4 angle. Mood: Performance. Precision. Driver focus. Add Bottom-right watermark: harboriis , with small x and Instagram logo