- PirateDiffusion
- 教學
- 如何提示
如何提示
PirateDiffusion 是聊天中的指令列。一則訊息產生一個渲染:指令、模型短碼、幾個參數和你的文字。本頁所有實例皆為 ModelTrends 目錄的真實渲染,指令可直接貼上使用。
Learn your first command: Skills
Type // to create or edit images and videos. You do not need to learn commands or pick a model first. Begin your request with two slashes and the bot picks the best Skill for it: the model, the workflow and the settings that fit your words. Copy this into the chat:
// a gray chubby cat napping in a sunny garden, photo
A confirmation message appears, then the pictures. The buttons under each result let you vote and upscale it.
Change the words and send it again. The more you describe, the closer the picture gets:
// a gray British shorthair cat asleep among peonies in a big garden, soft morning light, realistic photo
Videos work the same way
Ask for motion and the bot picks a video Skill:
// a short video of waves rolling onto a black sand beach at sunset
Edit a photo
Send a photo into the chat first, then reply to it with your request. Putting the word edit in it helps the bot pick an editing Skill:
// edit, make her hair blonde
Pick a Skill yourself
Every Skill also has a name you can run directly, for example /anime-illustrious a warrior standing in the rain. /skill /list shows the Skills available to you, /skill /show:name describes one, and /skill /tune lets you mute the ones you never want picked for you.
When you want full control
The /render and /workflow commands name the exact model, size, steps and seed yourself. That is what the How to prompt lessons and the commands list are for. The original SDXL beginner lesson, with its /render cat examples and bracket weights, is kept as a 2024 guide.
1. 渲染指令
以 /render 開頭,角括號內寫模型名稱,接著寫你想看到的內容。參數是斜線字詞,可放在訊息任意位置。
/render <krea2> /size:1024x1024 A fantasy knight in full armor with helmet. His sword at belt. In neutral pose. White background.
本頁範例使用 <krea2>,即 Flux Krea 基礎模型,解析度為 1024 像素;提示詞皆取自 ModelTrends 目錄中的真實範例。若未指定模型名稱,機器人將使用你的預設模型。只需更換 ShortCode 即可在其他模型上嘗試相同提示詞。
即時範例:ShortCode、渲染設定參數、提示詞及其負面提示。
/render <realism-enhancer-krea2> A minimalist, high-contrast studio portrait captures an orange tabby cat wearing a perfectly styled blonde wig with straight bangs, looking off-camera with a grumpy expression and wearing bright red lipstick, featuring rich composition grading and insane sharpness. The cat's smooth, light brown and white fur stands out sharply against a flat, deep dark blue background that serves as a vast expanse of clean negative space. The tight, centered flash composition highlights the realistic texture of the shiny blonde synthetic hair, the cat's long white whiskers, and the glossy red pout, creating a bizarre, authentic, and starkly humorous artistic study.
2. ModelTrends ShortCodes
ModelTrends.ai 上每個模型頁面都有一個 ShortCode 方塊。該 ShortCode 是 PirateDiffusion 中模型的名稱:將它放入指令中,機器人就會載入該模型。數千個模型、LoRA 和嵌入已預載,無需下載。
在機器人中,輸入 /concepts 可列出模型,/concept /search 可依名稱搜尋模型。
/concepts /concept /search:anime
瀏覽目錄,開啟模型並複製其 ShortCode: ModelTrends.ai
3. 參數
範例指令中的參數是原始渲染的設定。複製它們可得到相同風格的圖片;更改 seed 可產生新圖。
/size:1024x1024 | 寬度與高度(像素)。現有模型支援 1024 以上解析度;1024x1024 為正方形,1024x1536 為直向。 |
/portrait /tall /landscape /wide | 以形狀捷徑代替尺寸。 |
/steps:25 | 渲染的去噪步數;步數越多越慢。 |
/guidance:7 | 提示詞遵循程度。每個模型有其最佳範圍。 |
/seed:123456 | 隨機種子。相同的種子、guidance、採樣器和模型會產生相同圖片。 |
/sampler:dpm2m /karras | 採樣器,/karras 為具此模式的採樣器。單獨輸入 /sampler 可列出所有採樣器。 |
/clipskip:2 | 跳過文字編碼器的最後幾層;部分模型訓練時為 2。 |
/images:4 | 一次指令生成的圖片數量。 |
參數在所有語言中皆保持英文,機器人會照原文讀取。
4. 權重、正向與負向提示
雙括號 (( )) 讓詞語權重增加,雙中括號 [[ ]] 則降低權重。負向提示(要排除的元素)也放在中括號內,通常置於末尾。
/render <krea2> /size:1024x1024 sketch painting, a rock climber scaling a ((steep cliff)), icy winds, frozen landscape [[blurry, text, watermark]]
從其他工具複製的提示詞常帶有 (詞:1.3) 權重。加入 /parser:new,機器人即可讀取。
/render <krea2> /size:1024x1024 /parser:new sketch painting, a rock climber scaling a (steep cliff:1.3), icy winds, frozen landscape
在 SDXL 模型中,負向嵌入放在負向提示內並帶有強度,例如:
[[<fastnegative-xl:-2>]]
5. LoRA 與配方
LoRA 是一個小型模型,添加特定元素:角色、風格、攝影機動作等。它也有 ShortCode,使用方式與提示詞同在指令中。ModelTrends 頁面會標明 LoRA 適用的基礎模型;搭配該基礎模型效果最佳。
/render <realism-enhancer-krea2> A minimalist, high-contrast studio portrait captures an orange tabby cat wearing a perfectly styled blonde wig with straight bangs, looking off-camera with a grumpy expression and wearing bright red lipstick, featuring rich composition grading and insane sharpness. The cat's smooth, light brown and white fur stands out sharply against a flat, deep dark blue background that serves as a vast expanse of clean negative space. The tight, centered flash composition highlights the realistic texture of the shiny blonde synthetic hair, the cat's long white whiskers, and the glossy red pout, creating a bizarre, authentic, and starkly humorous artistic study.
配方是已保存的詞語與設定組合,以標籤呼叫。輸入 /recipes 可列出。
/render <krea2> /size:1024x1024 a fantasy knight in full armor, white background #boost
6. 工作流程:圖片、影片與音樂
工作流程是在 Graydient 伺服器上執行的完成任務:它會載入正確的模型和設定,所以你只需發送指令。圖片工作流程接受與 /render 相同的參數。例如 Krea2 工作流程:
/workflow /run:krea2 /size:1024x1024 a high quality real photo of a pirate with long black hair, a scraggly beard and mustache, wearing sunglasses, a gold chain necklace and a golden chalice, having pizza with a giant parrot pouring him champagne
影片與音訊模型以工作流程形式運行:/workflow /run: 加上工作流程的 slug,再接提示詞。ModelTrends 在工作流程的 ShortCode 方塊中顯示 slug,格式為 /wf /run:,是相同指令的簡寫。
slug 的第一個字說明工作流程接受的輸入類型:
video- | 文字轉影片:僅用提示詞生成影片片段。 |
animate- | 圖片轉影片:回覆一張圖片並輸入指令,提示詞說明要移動的部分。 |
omni- | 兩者皆可:可單用提示詞或回覆圖片。 |
影片 LoRA 放在 slug 與提示詞之間。為圖片輸入設計的 LoRA 仍可用於文字轉影片工作流程,但在回覆圖片並使用 animate 工作流程時效果最佳;範例卡片會說明。即時範例:
wan2.2-i2v-high-Screen Flood(屏幕淹水)
/workflow /run:video-wan22 <high-screen-flood-wan> then water suddenly rushes up from the bottom and submerges the entire screen.
搭配圖片輸入效果最佳:回覆一張圖片並改用 /run:animate-wan22。
工作流程可接受額外的插槽值,格式為 /slot1: 等,置於訊息末尾;每個工作流程頁面會說明插槽用途。音樂工作流程以歌詞為提示詞,曲風放在插槽中。
7. 從 ModelTrends 複製提示詞
ModelTrends 模型頁面上的每個範例渲染都有複製按鈕,會連同 PirateDiffusion 參數一併複製提示詞。貼到 /render 後面並加上模型 ShortCode 即可。
你可以用自己的語言撰寫提示詞。加上 /translate,機器人會先翻譯再渲染。
/render <krea2> /size:1024x1024 /translate un caballero de fantasía con armadura completa, fondo blanco
詳細版本(2024 SDXL 指南)
這些指南為 2024 年的 SDXL 撰寫。指令仍可使用;模型與尺寸與上述相同。
