Overview
The AI Image Generator node enables you to create and manipulate images using various AI models from different providers. This node supports multiple AI systems including StabilityAI, OpenAI, Replicate, Ideogram, and Flux, offering flexibility in choosing the best model for your specific image generation needs.
Input Configuration
Each input section can be expanded or collapsed by clicking the arrow icon next to the section name, allowing you to organize your workspace and focus on the fields you need.
Prompt Section
The primary input for your image generation request:
Purpose: Enter your main description of the image you want to generate
Connection Point: Can receive prompts from other workflow nodes
Best Practices: Be clear and specific about visual elements, style, composition, and details
Advanced Section
Provide additional parameters to fine-tune your image generation:
Subject Field: Specify the main subject or focus of your image
Environment Field: Describe the setting, background, or location
Tone Field: Set the mood, color scheme, or atmosphere
View Field: Indicate the perspective, angle, or viewpoint
Style Field: Define the artistic style or aesthetic direction
Negative Prompt Field: Specify elements to exclude from the image
Generation Modes
Choose from multiple image generation and editing modes:
Text to Image
Purpose: Create images from text descriptions
Input: Text prompt describing desired image
Output: Generated image based on description
Image to Image
Purpose: Transform existing images using AI
Input: Source image plus text prompt for modifications
Mode Options:
style: Apply artistic styles to input image
structure: Maintain composition while changing other elements
sketch: Convert line drawings into detailed images
Aspect Ratio: Select output proportions (1:1, etc.)
Influence Strength: Control how much the input image affects the result (0%-100%)
AI Edit
Purpose: Modify specific parts of existing images
Input: Source image plus editing instructions
Edit Modes:
using mask: Define specific areas to edit with mask overlay
using search prompt: Target elements by description in Search Prompt field
recolor using search: Change colors of described elements
AI Erase
Purpose: Remove unwanted elements from images
Input: Source image
Erase Modes:
remove objects: Intelligently remove specific objects
remove background: Automatically detect and remove backgrounds
Image Enhancement
Purpose: Improve image quality and resolution
Enhancement Types:
Enhance resolution: Increase image quality and detail
Expand Image: Extend image boundaries in specified directions
Expand Settings: Control expansion amount for Top, Left, Right, Bottom edges
Advanced Settings
Access detailed configuration options by clicking on the model dropdown at the bottom of the node interface. This opens the Advanced Settings panel where you can fine-tune various parameters for your selected AI model.
Model-Specific Parameters
StabilityAI Advanced Settings:
Engine: Select from available model versions through dropdown
Clip Guidance Preset: Choose guidance presets including NONE, FAST_BLUE, FAST_GREEN, SIMPLE, SLOW, SLOWER, SLOWEST to adjust prompt coherency
Sampler: Select sampling method from options including AUTO, DDIM, DDPM, K_DPMPP_2M, K_DPMPP_2S_ANCESTRAL, K_DPM_2, K_DPM_2_ANCESTRAL, K_EULER, K_EULER_ANCESTRAL, K_HEUN, K_LMS
Width & Height: Set image dimensions with sliders
CFG Scale: Control prompt adherence (1-20 range)
Steps: Set generation iterations (1-150 range)
Image Strength: Adjust input influence for image-to-image
Prompt Weight: Control prompt emphasis (0-2 range)
OpenAI Advanced Settings:
Open AI Models: Select from DALL-E models including DALL-E-2 and DALL-E-3
Quality: Choose between standard and hd output quality
Size: Select from available resolution options
Ideogram Advanced Settings:
Ideogram Models: Choose from V3, V3-TURBO, and V3-QUALITY models
Aspect Ratio: Select from available aspect ratio options
Style Type: Choose from AUTO, GENERAL, REALISTIC, and DESIGN artistic styles
Resolution: Pick from available output sizes
Magic Prompt: Select AUTO, ON, or OFF for enhanced prompt interpretation
Flux Advanced Settings:
Flux Models: Select from pro, pro-1.1, dev, and schnell models
Image Size: Choose from preset dimension options
Number of Inference Steps: Adjust generation iterations (1-50 range)
Seed: Set value for reproducible results
Classifier Free Guidance: Fine-tune prompt following (1-10 range)
Sync Mode: Toggle synchronized generation
Safety Tolerance: Adjust content filtering (1-5 range)
Output Configuration
Image Display
Main Output: Shows generated images in the Output section
Preview Area: Visual display of results with download options
Connection Point: Images can feed into other workflow nodes
Generation Management
Token Usage: Track consumption displayed at top
Model Indicator: Shows selected model and current settings
Processing Status: Visual feedback during generation
Execution Control
Run Prompt Button
Location: Top-right corner of the interface
Function: Initiates AI image generation
Visual Feedback: Button provides immediate response when clicked
Processing: Shows generation progress and completion
Best Practices
Prompt Optimization
Be Descriptive: Include specific details about composition, lighting, style, and subject matter
Use Visual Language: Describe colors, textures, lighting, and spatial relationships
Specify Style: Reference art movements, techniques, or specific aesthetic approaches
Include Technical Details: Mention camera settings, perspective, or rendering style when relevant
Model Selection Guidelines
StabilityAI: Choose for maximum parameter control and traditional workflows
OpenAI: Select for photorealistic results and natural language interpretation
Replicate: Use for experimental models and specialized applications
Ideogram: Pick for fast iterations and efficient processing
Flux: Select for professional applications requiring precise control
Parameter Tuning
Start with Defaults: Begin with standard settings and adjust based on results
CFG Scale Adjustment: Lower values for creative freedom, higher for strict prompt following
Steps Optimization: Balance quality with processing time
Resolution Considerations: Choose appropriate dimensions for intended use
Image-to-Image Guidelines
Influence Strength: Start at 50% and adjust based on desired transformation level
Input Quality: Use high-quality source images for better results
Prompt Alignment: Ensure text prompts complement rather than contradict the source image
Mode Selection: Choose appropriate mode (style/structure/sketch) for desired outcome
Integration Considerations
Workflow Integration
Input Connections: Connect prompts and parameters from other nodes
Output Usage: Generated images can feed into other processing nodes
Multi-Model Workflows: Use different models for different generation stages
Performance Optimization
Model Efficiency: Choose appropriate models for task complexity
Resolution Management: Balance quality with processing time
Batch Processing: Consider generating multiple variations efficiently
Quality Control: Implement validation steps for generated content
The AI Image Generator provides comprehensive image creation and editing capabilities with extensive model choices and fine-tuned control options, enabling sophisticated visual content workflows.