Japanese AI Image Result UI

Objective: To create a clean, screenshot-style webpage that displays suggestions based on prompts.{argument name="prompt text" default="Two women are sitting facing each other, each with their index finger on the other's lips."} The AI ​​image generation result. Canvas: 1030×630 horizontal screenshot, white background, minimalist modern chat UI, ample white space, no browser border or watermark. Layout: A rounded light blue-gray user prompt bubble is placed near the upper right corner, approximately 605 px wide and 90 px high, containing dark gray Japanese prompt text. Below on the left, a small blue gradient flashing icon is added, followed by the Japanese tag "思考プロセスを表示" (to express thinking pros) and a small downward arrow. Centered to the lower left of this icon, a rounded generated image card, approximately 570×310 px in size, is placed. Below the image on the left, four feedback/action icons are displayed side-by-side: like, dislike, a circular regenerated arrow, and a vertical three-dot menu. The generated image card content: A realistic snapshot of a coffee shop, showing two adult women sitting face-to-face at a small wooden table by a large window. The woman on the left is wearing {argument name="left woman outfit" default="beige knit sweater and dark skirt"} The woman on the right is wearing {argument name="right woman outfit" default="White top with a blue denim jacket"} They leaned towards each other, gently placing their index fingers on each other's lips in a playful yet intimate mirrored gesture. Their faces were deliberately anonymized, each with a soft rectangular pixel/blur mask. The table contained four visible items: a glass of water, a small white cup, a saucer or small plate, and a smartphone. The café background was warm and inviting, furnished with wooden furniture, cushions, bookshelves, plants, and natural light from the window, with several blurry customers in the distance. Visual style: The surrounding interface should be clean, flat, and Google-esque, while the image cards should be realistic, featuring warm natural light, shallow depth of field, and a documentary style. Japanese UI text should be used accurately in designated locations. The composition must faithfully reproduce the AI-generated image embedded in the chat interface.