原始文档
GPT Image 2.5 · en
Create one high-fidelity desktop web app screenshot for a fictional AI image-generation workbench called Canvas Forge. This is a single polished 16:9 product UI screen, not a collage or presentation.
Dark editorial interface with a left navigation rail, a central 3-column image-generation workspace, and a right inspector panel.
Exact readable text: Canvas Forge, New generation, Prompt, Reference image, Generate, Aspect ratio, 16:9, Model, GPT Image 2.5, Quality, High, Seed, 4821, Recent outputs.
Show one large generated image preview of a warm cinematic desert observatory at sunset in the center.
Use concise realistic labels, consistent spacing, clear hierarchy, accessible contrast, subtle borders, no gradients, no fake logos, no gibberish, no extra windows.
The screenshot should feel like a mature production creative tool with believable controls and useful empty states. Render every specified label exactly and keep all UI text short and legible.使用方法
- 复制完整原始提示词，并保留其中的参数。
- 按需求替换主体、文字和构图要求。
- 在兼容的外部工具中使用，核对当前使用条件并检查结果。
开始前需了解
- 先确认是否需要参考图。标注兼容模型，不代表该示例由这个模型生成。
- 核对名称、数字与画面文字；不同模型版本的结果可能不同。
