DressCode: Your AI Stylist for Tomorrow

DressCode is an AI-powered styling app built with Google's Gemma 4 that helps users choose weather-appropriate outfits by analyzing uploaded photos of their clothes. The app uses Gemma 4's image understanding to extract details like color, category, and seasonality from each clothing item, then combines this with weather forecast data to suggest complete, coordinated outfits. The system relies on structured JSON output via Pydantic schemas to organize clothing data efficiently, enabling intelligent wardrobe management without manual input.

This is a submission for the Gemma 4 Challenge: Write About Gemma 4 Getting dressed is often stressful. What should you wear when the weather keeps changing? DressCode makes it simple. Powered by Google’s Gemma 4 AI, this app helps you choose the right clothes for the weather tomorrow. Just upload photos of your clothes. The AI will describe each item, recognize the colors, and know if it’s for cold, warm, spring, or winter weather. Tell the app the date and time of your event. It checks the weather forecast and suggests complete outfits that match in style and color. DressCode saves you time and helps you look good every day. Smart. Simple. Always dressed right. To build DressCode, we rely on two main capabilities from Google’s Gemma 4 AI: If in a hurry, look for the core code here https://github.com/saad4software/dresscode-core and the backend code here https://github.com/saad4software/dresscode-back 1. Smart Clothing Analysis When users upload photos of their clothes, Gemma 4 analyzes the images and extracts as many details as possible to sort outfits, details like: - Identifies each piece of clothing shirt, pants, jacket, dress, etc. - Describes important details: color, pattern, style, material, and type - Determines weather suitability warm, cold, spring, winter, etc. This allows the app to understand the user’s wardrobe without manual input. 2. Weather-Based Outfit Generation Gemma 4 then uses the second key function: - Checks the weather forecast for the selected date and time day or night - Understands the season and weather conditions - Picks the best matching clothes from the user’s collection - Creates complete, well-coordinated outfits that match in color and style By combining powerful image understanding with smart reasoning, Gemma 4 turns your personal closet into an intelligent, weather-aware stylist. This is the core technology behind DressCode — making outfit decisions fast, easy, and always appropriate for the weather. Setup AI Studio project In order to use Gemma, we need an API key. and in order to get the key, we need to create a project https://aistudio.google.com/projects and after creating and naming the project, we can get the api key from the project. Setup the environment Using UV for the virtual environment, we only need the project file and sync the requirements project.toml project name = "dresscode" version = "0.1.0" description = "Add your description here" readme = "README.md" requires-python = " =3.12" dependencies = "google =3.0.0", "google-genai =2.4.0", "python-dotenv =1.2.2", "requests =2.34.2", uv sync Smart Clothing Analysis One of the most important features in DressCode is Smart Clothing Analysis. When a user uploads a photo of their clothes, the app needs to understand every item clearly and return the information in a clean, organized way. To achieve this, we use Gemma 4 with a structured prompt and JSON schema. Here’s how it works: Gemma 4 analyzes the image and identifies every distinct clothing item and accessory. It then returns the results as a well-organized JSON object. The model extracts key details for each item, including: - Item name - Category top, bottom, dress, shoes, etc. - Colors as hex codes - Dominant color - Warmth level - Season suitability - Style, material, pattern, formality, and more By using response mime type="application/json" and a strict Pydantic schema, we force Gemma 4 to return clean, consistent, and ready-to-use data. This makes it easy for the app to save each clothing item into the database without extra processing. This organized JSON output is the foundation of DressCode’s intelligent wardrobe system. It allows the AI to truly understand the user’s clothes before suggesting perfect outfits. We need to set up the GEMINI API KEY as an environment variable. Let's create a .env file and set it. GEMINI API KEY=AIz... Now for the clothes analysis script python from google import genai from dotenv import load dotenv from google.genai import types from pydantic import BaseModel, Field from typing import List load dotenv 1. Define the structure for a single clothing piece class ClothingItem BaseModel : name: str = Field description="Name or short description of the piece" category: str = Field description="Must be one of: Top, Bottom, Outerwear, Footwear" color palette: str = Field description="Dominant colors, e.g., Navy Blue, Warm Beige" seasonality: str = Field description="e.g., Heavy Winter, Light Spring, Hot Summer" style vibe: str = Field description="e.g., Formal, Casual, Streetwear, Athletic" location in image: str = Field description="where it is relative to the scene, e.g. 200, 123, 1000, 1000 '" 2. Define the container for the final list class ClosetAnalysis BaseModel : clothes: List ClothingItem client = genai.Client image path = "strikkeopskrift-p.jpg" with open image path, "rb" as f: image bytes = f.read response = client.models.generate content model="gemma-4-26b-a4b-it", contents= types.Part.from bytes data=image bytes, mime type="image/jpeg", , "Analyze the clothing pieces visible in this image and catalog them strictly according to the schema.", , config=types.GenerateContentConfig response mime type="application/json", response schema=ClosetAnalysis, , print response.text This script will generate a response following the schema provided, but for more details, I would update the analysis prompt to DRESS VISION PROMPT = "Analyze every distinct clothing item visible in this image and catalog " "each one as a separate entry in the items array, strictly according " "to the schema. Include ALL visible garments and wearable items: tops, " "bottoms, outerwear, dresses, shoes, socks, hats, bags, and accessories. " "Do not skip smaller or partial items—if shoes, socks, a hat, jewelry, " "a belt, scarf, tie, watch, or sunglasses are visible, each gets its own " "entry with the correct category: " "shoes for any footwear; socks for socks or visible hosiery; hat for " "hats, caps, and beanies; accessory for jewelry, belts, scarves, ties, " "watches, sunglasses, gloves, and similar add-ons; bag for handbags and " "backpacks. " "Do not merge multiple garments into one entry. " "If only one garment is visible, return a single-item array. " "Colors must be lowercase 7-character hex strings starting with ' '." And I would update the JSON response to allow multiple pieces of clothing. schemas.py python from datetime import datetime, timezone from typing import Optional from enum import Enum from pydantic import BaseModel, Field, field validator class Category str, Enum : top = "top" bottom = "bottom" outerwear = "outerwear" shoes = "shoes" accessory = "accessory" dress = "dress" underwear = "underwear" bag = "bag" hat = "hat" socks = "socks" other = "other" class WarmthLevel str, Enum : light = "light" medium = "medium" heavy = "heavy" class Season str, Enum : summer = "summer" winter = "winter" spring = "spring" fall = "fall" all season = "all season" class Layering str, Enum : base = "base" mid = "mid" outer = "outer" class Pattern str, Enum : solid = "solid" striped = "striped" plaid = "plaid" floral = "floral" graphic = "graphic" other = "other" class Formality str, Enum : casual = "casual" smart casual = "smart casual" business = "business" formal = "formal" class Brightness str, Enum : light = "light" dark = "dark" mixed = "mixed" class DressStatus str, Enum : draft = "draft" ready = "ready" needs review = "needs review" class DressVisionMultiResult BaseModel : """JSON schema sent to Gemma when cataloging all garments in one image.""" items: list "DressVisionResult" = Field min length=1, description= "One entry per distinct garment or wearable visible in the image " " e.g. top, bottom, shoes, socks, hat, accessory in an outfit photo " , class DressVisionResult BaseModel : """Vision metadata for a single clothing item.""" item name: str = Field description="Short human-readable name of the garment" category: Category = Field description="One of: top, bottom, outerwear, shoes, socks, accessory, " "dress, underwear, bag, hat, other" colors: list str = Field default factory=list, description="All visible colors as rrggbb hex strings", dominant color: str = Field description="Primary color as rrggbb" warmth level: WarmthLevel = Field description="One of: light, medium, heavy" season suitability: list Season = Field default factory=list, description="One or more of: summer, winter, spring, fall, all season", style: list str = Field default factory=list, description="Short style tags, e.g. casual, formal, streetwear", description: str = Field description="Concise visual description 1-3 sentences " layering: Layering = Field description="One of: base, mid, outer" pattern: Optional Pattern = Field default=None, description="One of: solid, striped, plaid, floral, graphic, other", material: Optional str = Field default=None, description="Best guess of fabric, e.g. cotton, wool, denim" formality: Optional Formality = Field default=None, description="One of: casual, smart casual, business, formal", brightness: Optional Brightness = Field default=None, description="One of: light, dark, mixed" water resistant: bool = Field default=False occasion tags: list str = Field default factory=list, description="Short occasion tags, e.g. work, party, outdoor, gym", confidence: Optional float = Field default=None, ge=0.0, le=1.0, description="Model confidence from 0 to 1" class DressCatalogItem BaseModel : """Slim wardrobe item shape sent to Gemma for outfit selection.""" id: int item name: Optional str = None category: Optional Category = None colors: list str = Field default factory=list dominant color: Optional str = None warmth level: Optional WarmthLevel = None season suitability: list Season = Field default factory=list style: list str = Field default factory=list formality: Optional Formality = None brightness: Optional Brightness = None layering: Optional Layering = None pattern: Optional Pattern = None material: Optional str = None water resistant: bool = False occasion tags: list str = Field default factory=list description: Optional str = None so the new process images script will look more like main.py python from google import genai from dotenv import load dotenv from google.genai import types from pydantic import BaseModel, Field from typing import List from enum import Enum from schemas import DressVisionMultiResult from scripts import DRESS VISION PROMPT load dotenv client = genai.Client image path = "outfit.jpg" with open image path, "rb" as f: image bytes = f.read response = client.models.generate content model="gemma-4-26b-a4b-it", contents= types.Part.from bytes data=image bytes, mime type="image/jpeg", , DRESS VISION PROMPT, , config=types.GenerateContentConfig response mime type="application/json", response schema=DressVisionMultiResult, , print response.text This is the model output for the image above { "items": { "item name": "light blue blazer", "category": "outerwear", "colors": " a5c7f7" , "dominant color": " a5c7f7", "warmth level": "medium", "season suitability": "summer", "spring" , "style": "smart casual" , "description": "A light blue single-breasted blazer with a pocket square.", "layering": "outer", "pattern": "solid", "material": "linen", "formality": "smart casual", "brightness": "light", "water resistant": false, "occasion tags": "work", "outdoor" , "confidence": 0.95 }, { "item name": "white dress shirt", "category": "top", "colors": " ffffff" , "dominant color": " ffffff", "warmth level": "light", "season suitability": "summer", "spring" , "style": "formal" , "description": "A crisp white button-down dress shirt.", "layering": "base", "pattern": "solid", "material": "cotton", "formality": "smart casual", "brightness": "light", "water resistant": false, "occasion tags": "work", "party" , "confidence": 0.98 }, { "item name": "white trousers", "category": "bottom", "colors": " ffffff" , "dominant color": " ffffff", "warmth level": "light", "season suitability": "summer", "spring" , "style": "smart casual" , "description": "A pair of slim-fit white trousers.", "layering": "base", "pattern": "solid", "material": "cotton", "formality": "smart casual", "brightness": "light", "water resistant": false, "occasion tags": "work", "outdoor" , "confidence": 0.95 }, { "item name": "dark brown leather belt", "category": "accessory", "colors": " 3b2b1e" , "dominant color": " 3b2b1e", "warmth level": "light", "season suitability": "all season" , "style": "classic" , "description": "A dark brown leather belt with a silver-tone buckle.", "layering": "base", "pattern": "solid", "material": "leather", "formality": "smart casual", "brightness": "dark", "water resistant": false, "occasion tags": "work" , "confidence": 0.9 }, { "item name": "sunglasses", "category": "accessory", "colors": " 1a1a1a" , "dominant color": " 1a1a1a", "warmth level": "light", "season suitability": "summer" , "style": "casual" , "description": "Dark sunglasses with black frames.", "layering": "base", "pattern": "solid", "material": null, "formality": "casual", "brightness": "dark", "water resistant": false, "occasion tags": "outdoor" , "confidence": 0.95 }, { "item name": "watch", "category": "accessory", "colors": " 000000" , "dominant color": " 000000", "warmth level": "light", "season suitability": "all season" , "style": "classic" , "description": "A black wristwatch with a dark face.", "layering": "base", "pattern": "solid", "material": null, "formality": "smart casual", "brightness": "dark", "water resistant": false, "occasion tags": "work" , "confidence": 0.85 }, { "item name": "dark brown loafers", "category": "shoes", "colors": " 3d2b1f" , "dominant color": " 3d2b1f", "warmth level": "light", "season suitability": "all season" , "style": "casual", "smart casual" , "description": "Dark brown leather loafers.", "layering": "base", "pattern": "solid", "material": "leather", "formality": "smart casual", "brightness": "dark", "water resistant": false, "occasion tags": "outdoor", "work" , "confidence": 0.92 } } I actually didn't notice the belt and watch, but someone - - seems to be watching every detail. Weather prediction After understanding the user’s clothes, DressCode uses Gemma 4’s function calling capability to handle the second key task. When the user selects a date, time, and city for their event or trip, the model makes a structured function call to fetch accurate weather information. Using function calling, Gemma 4 requests real-time weather data for the chosen city and date. It receives details such as temperature, weather conditions sunny, rainy, cloudy, etc. , and day/night timing. The model then analyzes this data together with the user’s clothing database to intelligently select and combine items. This allows Gemma 4 to consider warmth level, season suitability, and weather conditions before generating complete outfit recommendations that match in color, style, and appropriateness. By combining powerful image analysis with function calling for live weather, DressCode delivers smart and practical outfit suggestions every time. python import os import requests from google import genai from google.genai import types from dotenv import load dotenv load dotenv def fetch weather from api location: str - dict: """Hits Open-Meteo API to get real weather data.""" try: First, geocode the city name to get latitude and longitude geo url = f"https://geocoding-api.open-meteo.com/v1/search?name={location}&count=1&language=en&format=json" geo res = requests.get geo url .json if not geo res.get "results" : return {"error": f"Could not find location: {location}"} lat = geo res "results" 0 "latitude" lon = geo res "results" 0 "longitude" Second, get the weather using the coordinates weather url = f"https://api.open-meteo.com/v1/forecast?latitude={lat}&longitude={lon}&current=temperature 2m,relative humidity 2m,precipitation&daily=temperature 2m max,temperature 2m min,precipitation probability max&timezone=auto" weather data = requests.get weather url .json return { "location": location, "current temp celsius": weather data "current" "temperature 2m" , "current humidity": weather data "current" "relative humidity 2m" , "current precipitation mm": weather data "current" "precipitation" , "today max temp": weather data "daily" "temperature 2m max" 0 , "today min temp": weather data "daily" "temperature 2m min" 0 , "rain chance percentage": weather data "daily" "precipitation probability max" 0 } except Exception as e: return {"error": f"Failed to get weather data: {str e }"} Map function names to our actual python functions AVAILABLE TOOLS = { "get weather": fetch weather from api } get weather declaration = { "name": "get weather", "description": "Get current weather for a given location.", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "City name, e.g. 'Berlin', 'San Francisco'", }, }, "required": "location" , }, } client = genai.Client tools = types.Tool function declarations= get weather declaration config = types.GenerateContentConfig tools= tools user prompt = "Should I bring an umbrella to Berlin today?" print f"User: {user prompt}\n" Turn 1: Ask the model response = client.models.generate content model="gemma-4-26b-a4b-it", contents=user prompt, config=config, If the model decided it needs to use our tool if response.function calls: for fc in response.function calls: print f"🤖 Model requests function: {fc.name} with args {fc.args}" Execute the actual Python tool tool to call = AVAILABLE TOOLS fc.name Extract location safely from tool arguments tool output = tool to call location=fc.args "location" print f"🔌 Tool output fetched: {tool output}\n" Turn 2: Send the data back to the model so it can construct its answer final response = client.models.generate content model="gemma-4-26b-a4b-it", contents= Include the original prompt context user prompt, Include the tool request object the model generated response.candidates 0 .content, Provide the real world answer back matching the function ID types.Part.from function response name=fc.name, response={"result": tool output} , config=config Keep tools configuration attached print f"🤖 final AI Answer: {final response.text}" else: print f"🤖 AI Answer: {response.text}" Sometimes, when trying to call any query gemma we face this error google.genai.errors.ServerError: 500 INTERNAL. {'error': {'code': 500, 'message': 'Internal error encountered.', 'status': 'INTERNAL'}} I guess it is due to high demand that the servers sometimes fail. Just trying again usually works. User: Should I bring an umbrella to Berlin today? 🤖 Model requests function: get weather with args {'location': 'Berlin'} 🔌 Tool output fetched: {'location': 'Berlin', 'current temp celsius': 13.8, 'current humidity': 94, 'current precipitation mm': 0.0, 'today max temp': 19.5, 'today min temp': 13.8, 'rain chance percentage': 83} 🤖 final AI Answer: Yes, you should definitely bring an umbrella. There is an 83% chance of rain in Berlin today. Now, since we can get the weather prediction accurately, we need to write the outfit suggestion prompt Outfit suggestion, put it all together I've written this prompt for outfit suggestion OUTFIT SUGGESTION PROMPT = """You are a personal stylist. Pick complete outfits from the user's wardrobe for a specific event. Workflow: 1. Call the get weather function for the event city, passing the event date in ISO YYYY-MM-DD format, to retrieve the forecast temperature, precipitation, wind, sunrise, sunset . 2. Consider the event type, the date season , the start time / end time whether it falls during the day, night, or spans both around sunrise/sunset , and the weather. 3. Pick pieces ONLY from the provided wardrobe catalog using their integer id . Never invent items. 4. Build AT LEAST 2 distinct complete outfits. A complete outfit covers, at minimum, a top, a bottom, and shoes when matching items exist in the catalog a single dress category item replaces top+bottom . Add an outerwear piece when the forecast is cold, wet, or windy. Add accessories or bag/hat when appropriate. 5. Match formality to the event type: - business / formal - formality "business" or "formal" - smart casual / date night - "smart casual" or higher - casual / outdoor / sports / party - "casual" or "smart casual" as fits 6. Match warmth to the weather. Prefer water-resistant items if rain is likely. Prefer the right season suitability for the event date. 7. Ensure COLOR HARMONY across the pieces in each outfit. Use the hex colors in the catalog to reason about complementary, analogous, monochromatic, or neutral-anchor palettes. Briefly state the harmony you chose in color harmony . 8. Provide a short weather summary of the conditions you optimized for and a per-outfit reasoning . Return ONLY the structured JSON matching the response schema. """ And for the weather prediction, we need to get it for a certain date, so I've updated it to php def fetch weather from api location: str, date: str = None - dict: """Hits Open-Meteo API to get real weather data, optionally for a specific date.""" try: 1. Geocode the city name to get latitude and longitude geo url = f"https://geocoding-api.open-meteo.com/v1/search?name={location}&count=1&language=en&format=json" geo res = requests.get geo url .json if not geo res.get "results" : return {"error": f"Could not find location: {location}"} lat = geo res "results" 0 "latitude" lon = geo res "results" 0 "longitude" 2. Build the weather URL based on whether a date was provided Open-Meteo takes start date and end date in YYYY-MM-DD format for specific ranges base url = f"https://api.open-meteo.com/v1/forecast?latitude={lat}&longitude={lon}&timezone=auto" if date: weather url = f"{base url}&start date={date}&end date={date}&daily=temperature 2m max,temperature 2m min,precipitation probability max" else: Fallback to current/today's forecast if no date is provided weather url = f"{base url}&current=temperature 2m,relative humidity 2m,precipitation&daily=temperature 2m max,temperature 2m min,precipitation probability max" weather data = requests.get weather url .json If there's an API error response from open-meteo if "error" in weather data: return {"error": weather data "reason" } 3. Format response dynamically depending on what parameters were sent response = { "location": location, "date": date if date else "today", "today max temp": weather data "daily" "temperature 2m max" 0 , "today min temp": weather data "daily" "temperature 2m min" 0 , "rain chance percentage": weather data "daily" "precipitation probability max" 0 } Only add current conditions if we didn't look up a specific forecast date if "current" in weather data: response.update { "current temp celsius": weather data "current" "temperature 2m" , "current humidity": weather data "current" "relative humidity 2m" , "current precipitation mm": weather data "current" "precipitation" , } return response except Exception as e: return {"error": f"Failed to get weather data: {str e }"} Map function names to our actual python functions AVAILABLE TOOLS = { "get weather": fetch weather from api } Updated declaration schema to include the date parameter get weather declaration = { "name": "get weather", "description": "Get current or predicted weather for a given location and optional date.", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "City name, e.g. 'Berlin', 'San Francisco'", }, "date": { "type": "string", "description": "The specific date for the weather prediction in YYYY-MM-DD format. Optional: default to today if not provided.", } }, "required": "location" , }, } Now the user is expected to provide the event details and a list of clothes catalog . The event will be something like event payload = { "event type": "casual", "event date": "2026-06-01", "start time": None, "end time": None, "city": "Berlin", "season": "Spring", "title": "Walk in the park", "notes": "", } and the catalog will be a list of clothes from analyzing the images catalog = { "item name": "light blue blazer", "category": "outerwear", "colors": " a5c7f7" , "dominant color": " a5c7f7", ... The final user prompt would look like user prompt = f"{OUTFIT SUGGESTION PROMPT}\n\n" f"Event:\n{json.dumps event payload, indent=2 }\n\n" f"Wardrobe catalog {len catalog } items :\n" f"{json.dumps c for c in catalog , indent=2 }" Will it work? let's try it out { "weather summary": "A warm and sunny spring day with a high of 29.9°C and a low of 16.4°C. Low chance of rain 16% , making it perfect for light, breathable fabrics and outdoor activities.", "color harmony": "I utilized a palette of crisp whites and light blues anchored by deep brown leather tones to create a refreshing, airy, and sophisticated summer-ready look.", "outfits": { "outfit id": 1, "items": 1, 2, 4, 5, 6 , "reasoning": "This outfit is optimized for the warm peak temperatures. The all-white base shirt and trousers reflects sunlight to keep you cool during your walk. I've added sunglasses and a watch to keep the look effortless and casual for a park setting." }, { "outfit id": 2, "items": 0, 1, 2, 3, 6 , "reasoning": "For a slightly more elevated 'smart-casual' approach, I've layered the light blue linen blazer. The linen material is highly breathable for the 29°C weather, and the light blue complements the white base perfectly. The dark brown belt and loafers provide a classic, grounded finish." } } Interesting choices, especially since the closet we use is almost empty. In short DressCode is a complete pipeline that intelligently recommends outfits based on your actual wardrobe and upcoming weather conditions. Built with a focus on simplicity and efficiency, the system uses Gemma 4 as its core AI engine and runs inside a UV virtual environment. Based on our experiments in this article, the core proof of concept was built on those steps Wardrobe Ingestion Users place photos of their clothes in a folder called catalog. The application scans this folder and uses Gemma 4 to analyze each image. For every photo e.g., red jacket.jpg , it generates a detailed JSON description file red jacket.json containing the item’s name, colors, warmth level, season suitability, style tags, category, and rich visual description. If a matching JSON file already exists, the image is skipped to avoid redundant AI calls.Event Definition The user defines their plans by creating a simple event.json file containing the event title, date, time range, location, and occasion type.Weather Integration The system automatically fetches accurate weather forecast data for the specified date and location.Intelligent Outfit Generation DressCode reads all the clothing descriptions from the catalog folder, filters out unsuitable items wrong season, inadequate warmth, or mismatched style , and feeds the relevant clothing data along with the weather information and event details to Gemma 4. The model then generates well-coordinated outfit suggestions, taking into account color harmony, layering needs, day/night conditions, and the specific occasion. A sample of the system outfit suggestions These outfit suggestions were generated from the clothes images | graphic t-shirt top | grey sweat shorts bottom | navy blue lightning bolt sneakers shoes | |---|---|---| | wide brim sun hat hat | short sleeve shirt top | light blue pleated trousers bottom | |---|---|---| We learn from the "short sleeve shirt top " that the AI can sometimes only see the tops of things, just like us humans :D. So don't trust everything you see, even Gemma can make mistakes Notice that I didn't feed the images to the image-generation model but only the outfit description model. In an actual app, it would be nice to provide both clothes images and a user profile, and ask the image-generation models to generate the complete outfit. Actually, the profile image should be a full-body image of the user, so the app can show exactly how the suggested outfit will look on them. { "event": { "event type": "casual", "event date": "2026-06-01", "start time": null, "end time": null, "city": "Berlin", "season": "summer", "title": "Walk in the park", "notes": "" }, "season": "summer", "filtered item count": 11, "weather summary": "Warm summer day with a high of 29.9\u00b0C and low of 16.4\u00b0C. Very low chance of rain and light winds.", "outfits": { "name": "Sunny Park Casual", "color harmony": "A light, airy palette using beige e6e1d3 and light blue 8eb0d4 with navy accents 001a33 for a cohesive, summery feel.", "reasoning": "Perfect for a warm summer walk in the park. The linen-blend trousers and short-sleeve shirt are breathable for the 30\u00b0C high, while the sun hat provides protection.", "pieces": { "dress id": 3, "category": "top", "role": "top", "source image": "2ce384fd55b44d16bcc9bb3c12c9bf4a.webp", "item": { "id": 3, "item name": "short sleeve shirt", "category": "top", "colors": " e6e1d3" , "dominant color": " e6e1d3", "warmth level": "light", "season suitability": "summer", "spring" , "style": "casual" , "formality": "casual", "brightness": "light", "layering": "base", "pattern": "solid", "material": "linen", "water resistant": false, "occasion tags": "daily" , "description": "A light beige, short sleeve button-down shirt made of a lightweight fabric." } }, { "dress id": 14, "category": "bottom", "role": "bottom", "source image": "spc2402.webp", "item": { "id": 14, "item name": "light blue pleated trousers", "category": "bottom", "colors": " 8eb0d4" , "dominant color": " 8eb0d4", "warmth level": "medium", "season suitability": "spring", "summer", "fall" , "style": "casual", "relaxed" , "formality": "smart casual", "brightness": "light", "layering": "base", "pattern": "solid", "material": "linen blend", "water resistant": false, "occasion tags": "daily wear", "summer outings" , "description": "A pair of light blue trousers with a pleated front and an elasticated drawstring waist. The fabric appears to be a lightweight linen or cotton blend." } }, { "dress id": 7, "category": "shoes", "role": "shoes", "source image": "Buy-Best-Quality-IMPORTED-Full-Blue-Shoes-for-Men-NB02-at-Most-Affordable-Price-by-shopse.pk-in-Pakistan-1-1200x900.jpg", "item": { "id": 7, "item name": "navy blue lightning bolt sneakers", "category": "shoes", "colors": " 1e3a5f", " ffffff" , "dominant color": " 1e3a5f", "warmth level": "light", "season suitability": "all season" , "style": "streetwear", "casual" , "formality": "casual", "brightness": "mixed", "layering": "base", "pattern": "graphic", "material": "synthetic", "water resistant": false, "occasion tags": "lifestyle", "streetwear" , "description": "Navy blue sneakers with a large white lightning bolt graphic on the side and a thick platform sole." } }, { "dress id": 10, "category": "hat", "role": "accessory", "source image": "damenhut-elegant-blau-strohhut-sommer-s2024tiffany-11.282x0-portrait.jpg", "item": { "id": 10, "item name": "wide brim sun hat", "category": "hat", "colors": " 001a33" , "dominant color": " 001a33", "warmth level": "light", "season suitability": "summer", "spring" , "style": "elegant", "classic" , "formality": "formal", "brightness": "dark", "layering": "outer", "pattern": "solid", "material": "straw", "water resistant": false, "occasion tags": "outdoor", "garden party" , "description": "A large navy blue wide brim hat with a decorative band and a bow on the side." } } }, { "name": "Relaxed Summer Blue", "color harmony": "Monochromatic-leaning blue tones with neutral grey 808080 as an anchor.", "reasoning": "A very casual, comfortable option for walking. The graphic tee and sweat shorts are ideal for high temperatures, and the sneakers are perfect for a park stroll.", "pieces": { "dress id": 1, "category": "top", "role": "top", "source image": "0d93ccd6fd86dd88dbf1127957054b4f 384.webp", "item": { "id": 1, "item name": "graphic t-shirt", "category": "top", "colors": " a1c4fd" , "dominant color": " a1c4fd", "warmth level": "light", "season suitability": "summer", "spring" , "style": "casual", "streetwear" , "formality": "casual", "brightness": "light", "layering": "base", "pattern": "graphic", "material": "cotton", "water resistant": false, "occasion tags": "birthday", "casual" , "description": "A light blue short-sleeve t-shirt featuring a large black graphic text that says 'IT TOOK ME 30 Years to look this GOOD'." } }, { "dress id": 4, "category": "bottom", "role": "bottom", "source image": "4 97683d58-4c20-474b-b247-2b952b726a65.webp", "item": { "id": 4, "item name": "grey sweat shorts", "category": "bottom", "colors": " 808080", " ffffff" , "dominant color": " 808080", "warmth level": "light", "season suitability": "summer", "spring" , "style": "casual", "streetwear" , "formality": "casual", "brightness": "mixed", "layering": "base", "pattern": "solid", "material": "cotton", "water resistant": false, "occasion tags": "lounging", "outdoor", "gym" , "description": "A pair of grey marl sweat shorts with an elasticated waistband and white drawstrings." } }, { "dress id": 7, "category": "shoes", "role": "shoes", "source image": "Buy-Best-Quality-IMPORTED-Full-Blue-Shoes-for-Men-NB02-at-Most-Affordable-Price-by-shopse.pk-in-Pakistan-1-1200x900.jpg", "item": { "id": 7, "item name": "navy blue lightning bolt sneakers", "category": "shoes", "colors": " 1e3a5f", " ffffff" , "dominant color": " 1e3a5f", "warmth level": "light", "season suitability": "all season" , "style": "streetwear", "casual" , "formality": "casual", "brightness": "mixed", "layering": "base", "pattern": "graphic", "material": "synthetic", "water resistant": false, "occasion tags": "lifestyle", "streetwear" , "description": "Navy blue sneakers with a large white lightning bolt graphic on the side and a thick platform sole." } } } , "generated at": "2026-05-22T14:54:07.319053+00:00" } Unfortunately, Gemma can't generate images : . So we ask Google to pay more attention to image generation next time. I really liked the idea of Gemini Omni all-to-all model ; it sounds like magic, and I cannot wait to get my hands on it Did you like the idea? Would you like to build the complete app? Contact me here and show your support at the core code repo https://github.com/saad4software/dresscode-core and the backend code repo https://github.com/saad4software/dresscode-back