Make-A-Scene is an image creation tool that Meta has demonstrated. Users are required to enter a text-based prompt and a rough sketch of what they wish to produce.
According to the company, this may prevent someone from having “a strong sense of pride and ownership over the content” they requested the AI to produce. Make-A-Scene is meant to solve that issue by allowing users more choice over the type of art that is produced.
According to Meta “Prior state-of-the-art AI systems that generated awe-inspiring images primarily used a text description as input … But text prompts, like ‘a painting of a zebra riding a bike,’ generate images with compositions that can be difficult to predict”