A model-based estimate of an image’s aesthetic appeal, based on learned visual preferences.
For example, the LAION aesthetic predictor trains a prediction model on CLIP representations. Its score reflects preferences in particular data, rather than universal artistic quality or a direct measurement of text-image agreement.
Source: Official documentation.
An advanced prompt technique that assigns different text instructions to different regions of an image, providing independent content control for each area. It allows precise control over composition and layout.
An evaluation metric that measures how well a generated image aligns with the given text prompt. It quantifies prompt alignment by calculating the cosine similarity between text and image embeddings of the CLIP model.
A neural network architecture that adds additional control layers to diffusion models to specify structural conditions like pose, edges, and depth maps during image generation.
A fine-tuning method developed by Google that customizes AI models to a specific subject or style using just a few photos.
The process of customizing a pre-trained AI model by providing additional training on a specific task, style, or dataset.
Conditioning is the process of guiding an AI model to generate outputs based on specific inputs.