AI Glossary
Plain-English definitions for every term you'll hit while learning AI image, video, and audio generation. No jargon.
CFG Scale
CFG Scale (Classifier-Free Guidance) is a diffusion-model parameter that controls how strictly generation follows your text prompt. Low valu...
Checkpoint
A checkpoint is a snapshot of all the trained weights of an AI model at a specific point in training. For Stable Diffusion, a checkpoint is ...
ControlNet
ControlNet is a neural network architecture that adds spatial conditioning to AI image generation. Instead of relying on text alone, Control...
Diffusion Models
Diffusion models are a class of generative AI that learns to reverse a noising process — they start with pure random noise and iteratively r...
Inpainting
Inpainting uses AI to regenerate a selected region of an image while keeping the rest untouched. You mark the area to change (by drawing ove...
Latent Space
Latent space is the compressed mathematical representation an AI model learns internally to represent its inputs. For images, latent space i...
LoRA
LoRA (Low-Rank Adaptation) is a fine-tuning technique that teaches an AI model a new style, character, or concept by training a small adapte...
Negative Prompt
A negative prompt is a text input that tells a diffusion model what to avoid in the generated image. Common negative prompts include 'blurry...
Prompt Engineering
Prompt engineering is the craft of designing text prompts that produce optimal AI outputs. For image generation it covers subject, style, li...
Stable Diffusion
Stable Diffusion is an open-source latent diffusion model that generates images from text prompts. Released by Stability AI in 2022, it runs...