AI Prompting Terms Glossary

What it is: A setting that controls how closely the model follows your prompt versus how much creative freedom it takes. Low CFG (3–5): the model interprets loosely, more natural results. High CFG (8–12): the model follows your prompt rigidly, but can introduce artifacts and over-saturation. Most models work best between 5–7 for photorealism.

What it is: The number of denoising iterations the model performs during generation. More steps generally means more refined output, but with diminishing returns above 25–30. For most workflows: 20 steps for drafts, 25–30 for final output. Going above 50 rarely improves quality and significantly increases generation time.

What it is: A number that controls the randomness of generation. The same prompt with the same seed will produce the same output every time. Different seeds produce different outputs from the same prompt. Save seeds of outputs you like — they let you reproduce or iterate from a known starting point.

What it is: The algorithm the model uses to generate the image step by step. Different samplers produce different results even with identical settings. DPM++ 2M Karras is widely regarded as the best general-purpose sampler for photorealism. Euler a is faster but less detailed. DDIM is good for reproducibility.

What it is: A list of things you don't want the model to include in the output. Works by steering generation away from those concepts. Not supported by all models, but essential for those that do (SDXL, FLUX, ComfyUI pipelines). Common entries: CGI, plastic skin, airbrushed, watermark, blurry, extra fingers, deformed anatomy.

What it is: Used in img2img workflows. Controls how much the model changes the input image. 0.0 = no change at all. 1.0 = ignore the input, generate fresh. For upscaling and refinement: 0.35–0.50 preserves composition while improving detail. For significant changes: 0.55–0.75.

What it is: Using an existing image as the starting point for a new generation, combined with a text prompt. The model modifies the input image according to the prompt at the denoising strength you set. Used for upscaling, style transfer, lighting changes, and refinement of AI-generated images.

What it is: Editing a specific region of an image while leaving the rest unchanged. You mask the area you want to change, write a prompt for what should replace it, and the model regenerates only that region. Used for removing watermarks, changing backgrounds, fixing specific details, or replacing elements in an existing image.

What it is: A small add-on model trained to reproduce a specific style, person, or subject that the base model doesn't know about. LoRAs are layered on top of the base model and are activated with a trigger word in the prompt. Used to lock in a specific person's face, apply a distinctive art style, or reproduce product-specific aesthetics.

What it is: A conditioning system that uses a reference image to control composition, pose, or depth in the generated output. Types include: OpenPose (matches a specific body pose), Depth (matches spatial depth from a reference), Canny (matches edges and lines), IP-Adapter (copies style or face from a reference image).

What it is: How consistent the subject looks across frames in an AI-generated video. Poor temporal consistency means the character's face, clothing, or appearance changes between frames — a common failure mode in AI video. Improved by adding identity lock instructions: "same consistent face and features throughout every frame, no morphing."

What it is: A technique where you explicitly instruct the video model to maintain a consistent subject identity across all frames. Not a model setting — it's a prompt instruction. Add it explicitly: "same face, no identity drift, same clothing and features throughout every frame, no morphing."

What it is: A structured prompt format used for video generation that organizes instructions into labeled sections: [MOTION], [SUBJECT], [ENV], [CAMERA], [STYLE], [DURATION]. Originally developed for Seedance 2.0 but works across most video models. Separating motion from subject from environment prevents the model from conflating them.

What it is: Instructions given to an LLM before the conversation starts that define its role, behavior, constraints, and output format. Applied at the session level — the model refers back to it throughout the conversation. More powerful than a user prompt for controlling consistent behavior. Used to set personas, define tone, restrict topics, and specify output formats.

What it is: A setting that controls how random or creative the model's outputs are. 0 = deterministic, always the most probable next token (precise, factual, repetitive). 0.7 = balanced creativity and coherence (good default). 1.0+ = highly variable, creative, sometimes incoherent. Use low temperature for factual tasks, higher for creative writing.

What it is: The maximum amount of text an LLM can process in a single session — including your instructions, the conversation history, and any documents you've provided. Modern LLMs have context windows of 100K–2M tokens. When the context limit is reached, the model begins to forget earlier parts of the conversation.

What it is: A technique that instructs the LLM to reason through a problem step by step before giving an answer. Activated by phrases like "think step by step" or "reason through this before answering." Significantly improves accuracy on complex reasoning tasks, math problems, and multi-step decisions.