如何为 MOSS-Image 写提示词

最重要的规则

1. 1

   把一切都描述出来

   主体与动作、场景、镜头与构图、媒介、光线、材质和色调。你没写的部分,MOSS-Image 会替你决定,所以完整的一段话胜过简短的一句。

2. 2

   用引号标出确切的文字

   把文字放进双引号,并严格按照希望呈现的样子书写,同时说明位置和样式:门边的黑板招牌,用白色手写大写字母写着 "FRESH COFFEE $3"。

3. 3

   用英文写提示词

   英文的效果最好。需要渲染的文字请用它本身的语言写在引号里,比如在英文描述中放入中文店铺招牌。

4. 4

   用反向提示词去除总是出现的东西

   像 "worst quality, bad anatomy, watermark, jpeg artifact" 这样的简短列表,就能让大多数图片更干净。主提示词只描述你想要的内容。

5. 5

   关闭提示词增强

   它会在提示词末尾随机添加词语。一段详细的 MOSS-Image 提示词,保持你写的原样更好。

可参考的提示词

• 真实场景中的招牌

  A cozy bookstore cafe at night seen from the rainy street, warm light spilling from tall windows onto wet cobblestones. By the door stands a chalkboard sign that reads "FRESH COFFEE $3" in white hand-lettered capitals. Inside, shelves of books and a few readers at small wooden tables. Photo, eye level, 35mm, soft reflections in the puddles, muted teal street against amber interior light.

  为什么有效: 一段话涵盖整个场景,招牌上的文字被精确引用并描述了样式,镜头、光线和色调也都点明了。适合使用 3:2 的宽高比。

• 手写中文,在你想要的地方换行

  A wide view of a refrigerator beside a kitchen counter with a fruit bowl. A small yellow sticky note on the refrigerator door is handwritten in Chinese:
  "记得买牛奶和鸡蛋！
  牛奶两盒，鸡蛋一打。
  顺便带一袋面包。"

  为什么有效: 描述用英文书写,便条内容保持中文,并在每行手写字应该结束的地方加入真正的换行。便条内容是:“记得买牛奶和鸡蛋!两盒牛奶,一打鸡蛋。再带一袋面包。”

• 细致的人像

  An elderly lighthouse keeper in a heavy cable-knit wool sweater stands at the top of a spiral iron staircase, holding a brass oil lamp at chest height. Behind him, the great glass lens of the lighthouse glows gold; through the round, salt-stained windows, storm clouds and white-capped waves roll in at dusk. Weathered face, short gray beard, calm eyes looking just past the camera. 35mm film photograph, medium shot from slightly below, shallow depth of field. Warm lamplight on his face against the cold blue dusk outside. Muted palette of brass, navy, and slate.

  为什么有效: 画面的每个部分都有各自的细节,两种不同颜色的光通过对比来营造氛围,而不是靠情绪词。

• 用标签生成动漫插画

  best quality, highres, 1girl, solo, long blue hair, twin tails, futuristic stage outfit, holding a microphone, stage lights, cheering crowd in the background, dynamic angle

  为什么有效: MOSS-Image 也能读懂动漫风格的标签,顺序是先质量,再角色,最后是其他内容。动漫插画用标签,其他情况用句子。