Doudou selling fermented tofu at stall AI Image Prompt
Refer to the character image in the first picture, generate a video of Doudou selling fermented tofu at a stall: On the stall are jars of chili, pepper, Sichuan pepper, ginger powder, coarse and fine dried chili, as well as a stainless steel basin, transparent jars, bamboo boards of fermented tofu, and an iron spoon. Doudou stands in front of the stall. A young female customer comes up and pinches a piece of fermented tofu. Doudou reminds her that it is for sale. The customer says she will buy the entire board for 25 yuan. Doudou asks if she still wants the pinched piece. After getting a positive answer, Doudou uses the iron spoon to scrape the fermented tofu piece by piece from the bamboo board into the stainless steel basin. During the process, one piece accidentally falls off. Doudou offers to add one piece, then changes to three pieces. Next, Doudou asks about spiciness preference. The customer chooses extreme spicy. Doudou warns that the chili is very hot. The customer says she loves spicy food and can add more. Doudou then asks if she wants pepper powder. After getting a positive answer, Doudou scoops various seasonings into a transparent jar, adds salt, and mixes well. Doudou takes out a mineral water bottle with holes containing wine, pours a generous amount into the basin, saying more wine helps coating, then pours the mixed chili into the basin, shakes the basin left and right to coat the tofu. After coating, Doudou puts the coated tofu into a transparent jar, presses it down with a spoon because it's too full, pours the remaining chili into the jar, puts on a white inner lid with vent holes, plugs the vent holes, and tells the customer that it needs to be stored for 20 days before eating, and if the jar bulges, she can unplug the holes to release air. Finally, Doudou puts on the outer lid, says goodbye to the customer, and the customer leaves carrying the jar.
Content: Video generation script with subjects (Doudou and customer), scene (stall and props), action sequence, and dialogue. Relies on reference image for character appearance.
Pros: Detailed steps, clear dialogue and actions.
Cons: Too many steps may affect generation coherence.
Reference image: Clearly depends on reference image (character in first picture)
Source materials are collected from publicly accessible web pages. Contact us if a rights issue needs review. Copyright & Privacy