ArchDiffusion v4.2
ArchDiffusion v4.2 is our most advanced AI-powered multi-expert rendering engine for architectural visualization. It features an enhanced prompt building system with granular control over every aspect of the render - from camera angles and lighting to environmental elements and material finishes.
How it works: v4.2 uses an intelligent prompt builder that combines your description with expert-specific parameters. Each expert type (exterior, interior, masterplan, landscape, product, plan) has its own specialized parameters that are automatically woven into an optimized prompt for the AI rendering engine.
What's new in v4.2:
- • Expert-specific parameters for each domain (exterior, interior, masterplan, etc.)
- • 8 render styles: raw, photoreal, cgi_render, cad, freehand_sketch, clay_model, illustration, watercolor
- • Geometry modes: precise (accurate) vs creative (artistic freedom)
- • Granular environmental controls (greenery, vehicles, people, weather, time of day)
- • Interior-specific controls (room type, furnishing level, lighting mode, ambience)
- • Product-specific controls (background, lighting, material finish, shadow style)
Credit Cost: 4 credits per generation
Endpoint
POST https://api.mnmlai.dev/v1/archDiffusion-v42Request
Send a POST request with multipart/form-data containing your source image and design parameters. The API processes images asynchronously through expert-specific AI pipelines, returning a request ID for status tracking.
AI Prompt Enhancement v4.2
v4.2 features an advanced prompt builder that constructs optimized prompts based on your expert type, render style, and selected parameters. The system intelligently combines geometry blocks, sidebar parameters, and style-specific modifiers.
Example: An exterior request with render_style="photoreal", time_of_day="golden_hour", and greenery="lush" generates a comprehensive prompt with cinematic lighting, volumetric effects, and detailed environmental context.
Want full control?
Set render_style to "raw" to disable AI prompt enhancement and pass your prompt directly to the engine without any modifications.
Required Parameters
| Parameter | Type | Description |
|---|---|---|
imageRequired | File | Source architectural image (JPEG, PNG, WebP). Max 15MB, min 1KB |
promptRequired | String | Description of desired transformation (max 2000 characters) |
Common Parameters (All Expert Types)
| Parameter | Type | Default | Description |
|---|---|---|---|
expert_name | String | "exterior" | Expert mode: "exterior", "interior", "masterplan", "landscape", "plan", "product" |
render_style | String | "photoreal" | "raw", "photoreal", "cgi_render", "cad", "freehand_sketch", "clay_model", "illustration", "watercolor" |
geometry | String | "precise" | "precise" (accurate geometry) or "creative" (artistic freedom) |
view_mode | String | "auto" | "auto" or "manual" |
seed | Number | Random | Random seed for reproducible results (0-1000000) |
annotation | String | "false" | Enable annotations: "true" or "false" |
show_dimensions | String | "false" | Show dimensions: "true" or "false" |
reference_image_1-4 | File | None | Optional style reference images (up to 4) |
Exterior Parameters
| Parameter | Default | Options |
|---|---|---|
camera_angle | auto | auto, eye_level, elevation, low, elevated, aerial, top_down, close_up |
camera_direction | front | front, corner_right, right, back, left, corner_left |
site_context | auto | auto, urban, suburban, nature |
greenery | some | none, some, lush |
vehicles | few | none, few, many |
people | few | none, few, many |
street_props | off | off, on |
motion | subtle | off, subtle, long_exposure |
time_of_dayphotoreal only | auto | auto, day, morning, golden_hour, sunset, dusk, blue_hour, night |
weatherphotoreal only | clear | clear, overcast, cloudy, hazy, rain, fog, snow |
ground_wetnessphotoreal only | dry | dry, damp, wet |
Note: Environmental parameters like time_of_day, weather, and ground_wetness are only applied when render_style is set to photoreal. These parameters are ignored when using raw mode.
Interior Parameters
| Parameter | Default | Options |
|---|---|---|
room_type | living room | living room, bedroom, kitchen, bathroom, dining room, office, etc. |
room_style | Modern interior | Modern interior, Minimalism, Japandi, Industrial, Scandinavian, etc. |
furnishing_level | auto | auto, empty, minimal, moderate, full |
indoor_plants | auto | auto, none, some, lush |
interior_accessories | off | off, on |
lighting_mode | auto | auto, off, natural, artificial, mixed |
floor_finish | auto | auto, matte, reflective |
ambience | auto | auto, daylight, golden_hour, night |
Masterplan Parameters
| Parameter | Default | Options |
|---|---|---|
plan_mode | 3d | 3d, 2d |
urban_density | auto | auto, low, medium, high |
development_type | auto | auto, residential, commercial, mixed_use, industrial, institutional, recreational |
water_features | auto | auto, none, river, lake, coastal, fountains |
greenery | moderate | sparse, moderate, dense, forest |
Landscape Parameters
| Parameter | Default | Options |
|---|---|---|
landscape_style | modern | modern, traditional, japanese, tropical, mediterranean, desert, etc. |
vegetation | moderate | minimal, moderate, lush, wild |
water_features | none | none, pool, pond, fountain, stream, waterfall |
hardscape | minimal | minimal, moderate, extensive |
outdoor_furniture | none | none, minimal, moderate, full |
landscape_lighting | none | none, path, accent, dramatic, full |
Product Parameters
| Parameter | Default | Options |
|---|---|---|
product_category | furniture | furniture, lighting, decor, kitchenware, electronics, fashion, jewelry, packaging, industrial, automotive |
background | white | white, gradient, studio, contextual, transparent |
product_lighting | soft | soft, dramatic, natural, rim, flat |
material_finish | auto | auto, matte, glossy, metallic, wood, fabric, leather, glass, ceramic |
shadow_style | soft | none, contact, soft, dramatic, reflection |
Plan Parameters
| Parameter | Default | Options |
|---|---|---|
plan_view_mode | 2d | 2d, 3d |
drawing_style | architectural | architectural, schematic, presentation, technical |
color_mode | monochrome | monochrome, colored, gradient |
furniture_2d | outline | none, outline, filled, detailed |
wall_style | filled | outline, filled, hatched, poche |
view_type_3d | bird_eye | bird_eye, isometric, perspective, section |
Render Styles Guide
Available Render Styles
Response
The API processes your request asynchronously and immediately returns a response containing a unique request ID. Use this ID with the Status Check endpoint to monitor processing progress and retrieve the final generated image.
Success Response (200 OK)
{
"status": "success",
"id": "vysqf2nr0drmc0ctqx5tkdse48",
"prompt": "Modern commercial building with glass facade",
"expert_name": "exterior",
"parameters": {
"expertType": "exterior",
"renderStyle": "photoreal",
"referenceImageCount": 0,
"promptComponents": {
"geometry": "precise mode geometry description",
"sidebar": "environmental settings",
"style": "photoreal render style"
}
},
"credits": 96
}Code Examples
1. Basic Exterior Rendering
curl -X POST https://api.mnmlai.dev/v1/archDiffusion-v42 \
-H "Accept: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: multipart/form-data" \
-F "image=@/path/to/building.jpg" \
-F "prompt=Modern commercial building with glass facade" \
-F "expert_name=exterior" \
-F "render_style=photoreal"2. Interior with Full Parameters
curl -X POST https://api.mnmlai.dev/v1/archDiffusion-v42 \
-H "Accept: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: multipart/form-data" \
-F "image=@/path/to/room.jpg" \
-F "prompt=Luxury penthouse living room" \
-F "expert_name=interior" \
-F "render_style=photoreal" \
-F "room_type=living room" \
-F "room_style=Modern interior" \
-F "furnishing_level=full" \
-F "indoor_plants=some" \
-F "lighting_mode=natural" \
-F "ambience=golden_hour"3. Product Rendering
curl -X POST https://api.mnmlai.dev/v1/archDiffusion-v42 \
-H "Accept: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: multipart/form-data" \
-F "image=@/path/to/chair-sketch.jpg" \
-F "prompt=Designer lounge chair with walnut frame" \
-F "expert_name=product" \
-F "render_style=photoreal" \
-F "product_category=furniture" \
-F "background=studio" \
-F "product_lighting=soft" \
-F "material_finish=wood" \
-F "shadow_style=soft"4. Node.js Implementation
const FormData = require('form-data');
const fs = require('fs');
const axios = require('axios');
const form = new FormData();
form.append('image', fs.createReadStream('building.jpg'));
form.append('prompt', 'Modern residential building');
form.append('expert_name', 'exterior');
form.append('render_style', 'photoreal');
form.append('geometry', 'precise');
form.append('time_of_day', 'golden_hour');
form.append('greenery', 'lush');
form.append('weather', 'clear');
const response = await axios.post(
'https://api.mnmlai.dev/v1/archDiffusion-v42',
form,
{
headers: {
'Accept': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY',
...form.getHeaders()
}
}
);
console.log('Request ID:', response.data.id);
console.log('Remaining credits:', response.data.credits);5. Python Implementation
import requests
url = 'https://api.mnmlai.dev/v1/archDiffusion-v42'
files = {
'image': open('building.jpg', 'rb')
}
data = {
'prompt': 'Modern commercial building with glass facade',
'expert_name': 'exterior',
'render_style': 'photoreal',
'geometry': 'precise',
'camera_angle': 'eye_level',
'time_of_day': 'golden_hour',
'greenery': 'some',
'vehicles': 'few',
'people': 'few'
}
headers = {
'Accept': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY'
}
response = requests.post(url, headers=headers, files=files, data=data)
result = response.json()
print(f"Request ID: {result['id']}")
print(f"Remaining credits: {result['credits']}")Checking Processing Status
GET https://api.mnmlai.dev/v1/status/{id}Processing Time: Typically 30-60 seconds. Poll the status endpoint every 3-5 seconds until the status becomes "succeeded" or "failed".
Best Practices
Image Guidelines
- Use high-quality source images (1024px or larger recommended)
- Supported formats: JPEG, PNG, WebP
- File size: 1KB - 15MB per image
- Images are automatically resized to 1344px width
Geometry Mode Selection
- precise: Maximum architectural accuracy, preserves exact geometry - best for technical visualizations
- creative: More artistic freedom, enhanced details - best for conceptual presentations
Expert-Specific Tips
- Exterior: Use time_of_day and weather for dramatic atmospheric effects
- Interior: Match room_style with furnishing_level for cohesive results
- Product: Use studio background with soft lighting for clean product shots
- Masterplan: Use 3d plan_mode with aerial camera for urban visualizations
Error Handling
Common Error Responses
// 400 Bad Request - Missing image
{
"status": "error",
"code": "MISSING_IMAGE",
"message": "Image file is required"
}
// 400 Bad Request - Insufficient credits
{
"status": "error",
"code": "NO_CREDITS",
"message": "You do not have enough credits to use this feature. This API requires 4 credits.",
"details": { "credits": 2, "required": 4 }
}
// 400 Bad Request - Image too large
{
"status": "error",
"code": "IMAGE_TOO_LARGE",
"message": "Image file is too large",
"details": { "size": 20000000, "maxSize": 15728640 }
}