Copy-ready prompt
Objective: Create a realistic ChatGPT-style webpage screenshot showcasing the generated images of game assets, including Japanese UI text and four generated asset thumbnails. Canvas: Landscape browser/application screenshot, approximately 797×750 pixels, white background, minimalist interface, cropped to only show the assistant's reply area and the image row at the bottom. Layout: A rounded light gray user message bubble is placed at the top center, containing the following content:{argument name="user request text" default="Use ImageGen to individually generate four images that could be used as assets in a game, and then try turning each of them into a 3D model!"} Below this, aligned to the left, a line of small gray text appears in the status bar: "25m 50s 作业しました〉", followed by a thin horizontal dividing line. Below this, a Japanese assistant reply is created, containing a file list and blue clickable file links. The text content includes the assistant paragraph: "できました。4枚のゲーム向けアセット影像を生成して、それぞれPixal3DでGLB化まで通しました。". This is followed by the tag "影像:", followed by four list links with small image/file icons: 1) mana_crystal_alpha.png, 2) treasure_chest_alpha.png, 3) energy_turret_alpha.png, 4) mushroom_house_alpha.png. Next is the tag "3D-ified GLB:", followed by four list links with document icons: 1) mana_crystal.glb, 2) treasure_chest.glb, 3) energy_turret.glb, 4) mushroom_house.glb. Finally, the closing text is added: "Generated is a magical crystal, a treasure chest, an SF energy treasure chest, a home. The background is transparent and 3D-ified." The bottom image bar displays four rounded square thumbnail cards in a horizontal row, each approximately 178 x 178 pixels, with moderate spacing. Thumbnail 1 features a vibrant green chroma key background and stylized fantasy.{argument name="asset one" default="blue mana crystal obelisk on a dark stone base"} Thumbnail 2 features a vibrant green chroma key background and{argument name="asset two" default="wooden treasure chest with dark metal bands, gold lock, and red jewel"} Thumbnail 3 features a vibrant green chroma key background and{argument name="asset three" default="gray sci-fi energy turret with blue glowing core and cannon barrel"} Thumbnail 4 has a bright magenta chroma key background and{argument name="asset four" default="cute mushroom house with red spotted cap roof, wooden door, and warm windows"} All four assets are exquisitely crafted 3D game art icons, featuring transparent cutout lighting, centered, and displayed independently. Visual Style: Modern ChatGPT interface screenshots, Japanese font, black body text, blue link text, small monochrome icons, ample white space, and delicate dividing lines. Asset thumbnails should resemble high-quality mobile game items, rendered in a richly colored, semi-realistic 3D style. Constraints: A total of 8 file links are required, specifically 4 PNG links and 4 GLB links, plus 4 asset thumbnails. Do not add extra panels, watermarks, browser borders, avatars, or irrelevant UI controls.
Prompt breakdown
Objective: Create a realistic ChatGPT-style webpage screenshot showcasing the generated images of game assets, including Japanese UI text and four generated asset thumbnails.
Canvas: Landscape browser/application screenshot, approximately 797×750 pixels, white background, minimalist interface, cropped to only show the assistant's reply area and the image row at the bottom.
Layout: A rounded light gray user message bubble is placed at the top center, containing the following content:{argument name="user request text" default="Use ImageGen to individually generate four images that could be used as assets in a game, and then try turning each of them into a 3D model!"} Below this, aligned to the left, a line of small gray text appears in the status bar: "25m 50s 作业しました〉", followed by a thin horizontal dividing line.
Below this, a Japanese assistant reply is created, containing a file list and blue clickable file links.










