Chapter 4. Beyond text-to-image prompting

While most AI-generated images start with a prompt, your creative journey doesn’t have to end there. In this chapter, we move beyond text-to-image workflows and explore powerful techniques for transforming, remixing, and extending your visuals using both images and sketches.

We begin with removing background and resizing images, a practical foundation for turning raw AI outputs into usable assets. You’ll learn how to isolate characters like Furferno, adjust aspect ratios for different platforms, and integrate these elements into new backgrounds—all using conversational tools or free web apps.

Next, we explore remixing images, which opens up endless creative possibilities. Whether you're adjusting a character’s color palette, changing art styles, or overlaying elements into different scenes, this section helps you develop versatile visuals tailored to different formats, moods, or use cases.

From there, we introduce the image-to-prompt-to-image technique—a creative loop that turns images into structured prompts, and then uses those prompts to generate new visual variations. This reverse-engineering process helps you analyze what makes an image compelling and reuse those ideas to build a consistent visual series.

We then dive into blending images, where two visuals are merged to create new characters or scenes. Whether you’re fusing mountain landscapes with cosmic profiles or combining stylistic traits from different portraits, this technique highlights how style, texture, and structure can harmonize into something entirely new.

Finally, we explore sketch to image, a method for converting your rough hand-drawn ideas into polished AI-generated artwork. You’ll see how simple pencil sketches can be transformed into full digital illustrations, preserving layout and tone while enriching detail, color, and emotion.