Two cats selling breakfast with Shanghai dialect AI Image Prompt
Two cats. In the first image, a kitten wears a yellow bib; in the second image, a kitten wears a red bib. Both kittens' bibs are printed with fortune cat pancakes. They wear sleeves and are busy at a stall. In the first image, the kitten on the left is frying youtiao and zifangao in a wok; in the second image, the kitten on the right is packing orders. The stall has dabing, youtiao, zifangao, and soy milk. Customers are queueing. Customer A: 'Boss lady, I want one dabing, youtiao, and a cup of soy milk.' The kitten in the second image packs and says: 'Okay, okay, (handing over a bag with dabing, youtiao, and soy milk) here you go, careful, it's hot.' Customer B: 'Boss lady, I want two pieces of zifangao.' The kitten in the second image says: 'Okay, coming right up, two pieces for five jiao, please scan the code yourself.' The kitten in the first image, while flipping the dabing in the wok, says: 'Don't worry, everyone, one at a time, it's coming fast.' Both kittens talk while working. The entire conversation is in Shanghai dialect, with childlike voices for the kittens and adult voices for the customers. Subtitles are provided. Speaking speed is moderate.
Content: Multi-image narrative prompt. Structure: subjects (two kittens, different bibs) → scene (pancake stall) → actions (frying, packing) → dialogue (Shanghai dialect, child/adult voices) → multimedia (subtitles, speed). Lacks visual style, lighting, color, camera, etc. for image generation.
Pros: Clear role division, rich dialogue details, suitable for multi-frame animation scripts.
Cons: Over-reliant on sequential images; single static image cannot show dialogue and voice; no visual style specified, leading to inconsistent generation.
Reference image: Clearly dependent on reference images (first image, second image)
Source materials are collected from publicly accessible web pages. Contact us if a rights issue needs review. Copyright & Privacy