AI Design Glossary

The tendency of AI models to generate non-real, fabricated, or incorrect information/content. It manifests differently in text, image, and video generation.

An interface through which software components communicate using defined operations and data formats.

A field concerned with computer systems performing tasks such as perception, prediction or content generation.

The FID Score is a standard evaluation metric used to measure the quality and realism of generated images.

The use of a graphics processor to perform many computational operations in parallel.

The process where a trained AI model makes predictions or generates output on new inputs. In image generation, it corresponds to converting a prompt into an image.

An approach to developing models that learn patterns from data for prediction or content generation.

A saved model state containing weights and sometimes additional information needed to resume training.

The process of adjusting model parameters using data and a learning objective.

A text command that defines unwanted elements in AI image generation. The model generates images while avoiding the elements specified in the negative prompt.

A text-based instruction or command given to AI models. It is used to describe the desired output and guides the model's generation process.

A discipline that encompasses techniques and strategies for writing prompts to get the best results from AI models. It includes proper word choice, structuring, and parameter usage.

The basic unit used by AI models when processing text. It can be a word, word fragment, or character. Prompt length and model capacity are measured in token count.

Zero-shot learning is the ability to perform tasks never seen in training data using only general knowledge.