Glossary

A generative model that learns to reverse a noise process to generate data. It works by gradually removing noise from random data to create meaningful outputs.

A powerful and modular stable diffusion GUI and backend. It uses a node-based interface for creating complex workflows.

Variational Autoencoder - a neural network that compresses images into a latent space and can decode them back to pixel space.

A U-shaped neural network architecture commonly used in diffusion models for denoising. It processes data through downsampling and upsampling layers.

A compressed representation of data in a lower-dimensional space. In diffusion models, images are processed in latent space for efficiency.

Text input that describes what you want to generate. The model uses this to guide the image generation process.

Classifier-Free Guidance scale - controls how closely the model follows the prompt. Higher values make the model follow the prompt more strictly.

The number of denoising steps the model takes to generate an image. More steps generally mean higher quality but longer generation time.

A saved model file containing the trained weights of a neural network. Different checkpoints can produce different styles and capabilities.

Low-Rank Adaptation - a technique for fine-tuning large models efficiently. LoRA files can add specific styles or concepts to a base model.

A latent diffusion model for generating high-quality images from text descriptions. It combines diffusion models with latent space processing for efficiency.

Contrastive Language-Image Pre-training - a neural network that learns to associate images with text descriptions.

A neural network component that converts text prompts into numerical embeddings that can guide the image generation process.

A predefined sequence that determines how much noise is added at each step of the diffusion process.

The process of removing noise from data. In diffusion models, this is the core mechanism for generating images.

An algorithm that determines how the denoising process is performed. Different samplers can produce different results.

A random number that initializes the generation process. The same seed with the same prompt will produce the same image.

Text that describes what you don't want in the generated image. It helps guide the model away from unwanted elements.

A numerical representation of data in a high-dimensional space. Text and images are converted to embeddings for processing.

A sequence of connected nodes in ComfyUI that defines how images are processed and generated.

A visual component in ComfyUI that performs a specific function, such as loading models or processing images.

A neural network that allows precise control over image generation by using additional input conditions like poses or edges.

The process of filling in or modifying specific parts of an existing image while keeping the rest unchanged.

The process of extending an image beyond its original boundaries by generating new content.

The process of increasing the resolution of an image using AI models to add detail and improve quality.

The process of improving the quality and detail of faces in generated or low-quality images.

The process of applying the artistic style of one image to another while preserving the content.

A small neural network that modifies the behavior of a larger model to achieve specific styles or effects.

A technique that learns to represent specific concepts or styles as text embeddings that can be used in prompts.

A technique for fine-tuning diffusion models to generate images of specific subjects using just a few example images.

A model that allows image prompts to guide text-to-image generation, enabling style and content transfer.

A diffusion model that operates in latent space rather than pixel space, making it more efficient for high-resolution image generation.

A mechanism in neural networks that allows different modalities (like text and images) to interact and influence each other.

A mechanism that allows neural networks to focus on different parts of the input data when making predictions.

A neural network architecture based on attention mechanisms that has revolutionized natural language processing and computer vision.

A connection that allows information to flow directly from one layer to another, helping with training deep networks.

A technique that normalizes the inputs to each layer, helping with training stability and convergence.

A regularization technique that randomly sets some neurons to zero during training to prevent overfitting.

A hyperparameter that controls how much the model weights are updated during training.

An optimization algorithm that iteratively adjusts model parameters to minimize the loss function.

A function that measures how well the model's predictions match the actual data, used to guide training.

When a model learns the training data too well and performs poorly on new, unseen data.

When a model is too simple to capture the underlying patterns in the data.

Techniques used to artificially increase the size of the training dataset by creating variations of existing data.

A technique where a model trained on one task is adapted for use on a different but related task.

The process of adapting a pre-trained model to a specific task or dataset by training it further.

The initial training phase where a model learns general features from a large, diverse dataset.

The process of using a trained model to make predictions or generate new data.

Graphics Processing Unit - specialized hardware that can perform many calculations in parallel, essential for AI model training and inference.

Video Random Access Memory - the memory on a graphics card that stores data for GPU processing.

A promptable segmentation model by Meta AI that can segment any object in an image. It was trained on 11M images and 1B masks, providing zero-shot segmentation capabilities.

A family of real-time object detection models that can identify and locate multiple objects in images. YOLO processes the entire image in a single pass, making it extremely fast.

The latest version of YOLO by Ultralytics featuring an anchor-free approach, CSPNet backbone for enhanced feature extraction, and FPN+PAN neck for superior multi-scale object detection.

A rectangular annotation that defines the location and size of an object within an image. Bounding boxes are defined by coordinates (x, y, width, height) or corner coordinates.

The process of partitioning an image into multiple segments or regions, typically to identify objects and boundaries. Can be semantic (classifying pixels) or instance-based (identifying individual objects).

DPM-Solver++ is a high-order solver for diffusion models that can generate high-quality samples in 15-20 steps. It solves the diffusion ODE with improved efficiency and quality.

A noise schedule based on the paper 'Elucidating the Design Space of Diffusion-Based Generative Models' by Karras et al. It applies a smaller amount of noise per step near the end of sampling for improved quality.

A templating system for prompts that allows random selection from predefined lists of terms. Wildcards use the syntax __filename__ to insert random values from text files.

A technique that divides large images into smaller tiles, processes each independently, and seamlessly stitches them together. Based on MultiDiffusion and Mixture of Diffusers algorithms.

A method for fusing diffusion paths to enable controlled image generation at high resolutions. It allows for panorama generation and region-based text control by processing overlapping tiles.

A workflow component that detects faces in generated images and applies targeted enhancement, including upscaling, denoising, and feature refinement to improve facial quality.

A stochastic sampler that uses the Euler method with added noise at each step. The 'ancestral' variant adds randomness, producing more varied results but less deterministic outputs.

A mask processing technique that softens the edges of a mask by gradually transitioning from opaque to transparent. This creates smoother blending between masked and unmasked regions.

A confidence value (0.0 to 1.0) that determines the minimum certainty required for an object detector to report a detection. Higher thresholds reduce false positives but may miss objects.

A morphological operation that expands the boundaries of regions in a binary image or mask. In object detection, it's used to expand bounding boxes or masks to include surrounding context.

A core ComfyUI node that performs the denoising process to generate images. It controls sampling steps, CFG scale, sampler type, scheduler, and seed for the generation process.

An advanced upscaling technique that uses tiled diffusion to upscale images to very high resolutions. It includes seam fixing and supports multiple upscale models.

A technique for high-resolution image generation that combines multiple diffusion models or regions. Each region can have different prompts or settings, enabling complex scene composition.

A computer vision task that identifies each distinct object in an image and creates a separate segmentation mask for each instance, even for objects of the same class.

A parameter (0.0 to 1.0) that controls how much the AI modifies an input image. Lower values preserve more of the original, while higher values allow more creative freedom.

A collection of vertices, edges, and faces that defines the surface geometry of a 3D object. Meshes are the most common representation for real-time rendering, animation, and 3D printing.

A point in 3D space defined by coordinates (x, y, z). Vertices are connected by edges to form faces, which together make up a mesh.

A flat face on a 3D mesh, typically made of three or more vertices. Triangles and quads are the most common polygon types in 3D graphics.

The process of projecting a 2D texture image onto a 3D mesh surface by assigning 2D coordinates (U, V) to each vertex.

A shading approach that simulates how light interacts with real-world materials using physically accurate properties like roughness, metallic, and normal maps.

A texture that stores surface normal direction per pixel, creating the illusion of fine geometric detail without adding polygons.

The structure and flow of polygons across a 3D mesh, including edge loops and face distribution. Good topology is essential for deformation and animation.

The process of rebuilding a mesh with cleaner polygon flow, usually to reduce polygon count or fix topology issues while preserving shape.

The process of creating a skeleton (armature) and assigning skin weights to a mesh so it can be posed and animated.

A technique that uses multiple versions of a model at different polygon counts, swapping to simpler meshes at greater distances to save performance.

A set of data points in 3D space, each with position and optionally color or normal information. Point clouds are common intermediate outputs in 3D scanning and reconstruction.

A volumetric pixel — a value on a regular 3D grid. Voxel representations are used in medical imaging, Minecraft-style worlds, and some 3D generation models.

GL Transmission Format — an open standard 3D file format optimized for efficient transmission and loading on the web and in real-time engines.

A 2D image where each pixel value represents the distance from the camera to the scene surface. Depth maps are key inputs for single-image 3D reconstruction.

The science of extracting 3D measurements and geometry from photographs by analyzing overlapping images of a subject from multiple angles.

A neural network that represents a 3D scene as a continuous volumetric function, encoding color and density at any point in space. NeRFs excel at photorealistic novel view synthesis.

3D Gaussian Splatting (3DGS) represents a scene as millions of colored 3D Gaussians that are rasterized in real time. It achieves NeRF-quality visuals with much faster rendering.

A function that maps any 3D point and viewing direction to emitted color and opacity. NeRFs and Gaussian splats are both radiance field representations.

Instant Neural Graphics Primitives — a method by NVIDIA that uses multi-resolution hash encodings to train NeRFs and other neural fields in seconds instead of hours.

A mathematical function that returns the shortest distance from any point in space to the nearest surface, with sign indicating inside or outside. SDFs define smooth implicit 3D shapes.

An algorithm that extracts a polygonal mesh from a 3D scalar field (such as an SDF or voxel grid) by identifying surface crossings between grid cells.

AI generation of 3D assets directly from text descriptions, typically using diffusion models, NeRF optimization, or large 3D datasets.

AI reconstruction of a 3D model from one or more 2D images, using depth estimation, multi-view diffusion, or neural field optimization.

Generating images of a scene from camera viewpoints that were not in the original input, requiring the model to understand 3D structure and appearance.

Building a 3D representation of a scene or object by combining information from multiple images taken from different viewpoints.

An open-source image-to-3D model by Tripo AI that generates textured 3D meshes from a single image in seconds using a transformer-based architecture.

An OpenAI model that generates 3D assets from text or images by decoding implicit functions into textured meshes or NeRFs, trained on a large corpus of 3D data.

A pioneering text-to-3D method that optimizes a NeRF using a pretrained 2D diffusion model as a score distillation signal, generating 3D without 3D training data.

A technique that uses gradients from a pretrained 2D diffusion model to optimize a 3D representation, enabling text-to-3D without paired text-3D datasets.

The post-processing step of converting an implicit or volumetric 3D representation (NeRF, SDF, voxels) into an explicit triangle mesh for editing and export.