In this paper, we explore the impact of task-specific prompt assistants for text-to-image generative AI tools through a user study. Participants were asked to recreate a dress with SDXL using either a prompt assistant tailored to the dress design, or, no assistant at all. A detailed analysis of the results and feedback suggests that for this specific task, a tailored assistant improves result satisfaction and accuracy. This style of assistant helps users focus on the task by providing a detailed, visual and organized approach to describing the object—enabling faster production times and more accurate descriptions with less ambiguity.

Gesture drawing is a type of fluid, fast sketch with loose and roughly drawn lines which capture the motion and feeling of a subject. While style transfer methods, which are able to learn a style from an input image and apply it to a secondary image, can reproduce many styles, they are currently unable to produce the flowing strokes of gesture drawings. In this paper, we present a method to produce gesture drawings, which roughly depict objects or scenes with loose, dancing contours, and frantic textures. Our method adapts stroke-based painterly rendering algorithms to produce long, curved strokes by following the gradient field. A rough, overdrawn appearance is created through progressive refinement.Additionally, we produce rough hatch strokes by altering stroke direction. These add optional shading to the gesture drawings. The wealth parameters that provide users the ability to adjust the output style from short, rapid strokes to long, fluid strokes, from swirling to straight lines. Potential stylistic outputs also include pen-and-ink and coloured pencil. We present several generated gesture drawings and discuss how our method can be applied to video. Our stroke-based rendering algorithm produces convincing gesture drawings with numerous controllable parameters permitting the creation of a variety of styles.