ideogram
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseIdeogram (image prompt craft)
Ideogram(图像提示词编写)
Write prompts that get design-grade images with correct text and deliberate layout out of
Ideogram (Ideogram 4.0). This is the prompt-craft layer of a three-layer setup, and the
typography/layout sibling to under the image-prompt router.
nano-banana- Connection/API (per-image pricing, MCP, the generate → upload to WoopSocial Media → attach
flow) → .
tools/integrations/ideogram.md - Prompt craft (this skill) → how to direct the right asset well.
- Router → picks the tool for the job.
image-prompt
This skill covers both lanes: generation prompt-craft (below) and the Ideogram app-editor workflow (Canvas, Magic Fill, Extend, Style References, Magic Prompt, Layerize) — for in-editor work, see. Re-verify model/specs quarterly.references/app-editor-and-canvas.md
编写提示词,让 Ideogram(Ideogram 4.0)生成
文字正确、布局精心且达到设计级质量的图像。这是三层架构中的 prompt-craft 层,也是
image-prompt 路由器下专注于字体排版/布局的 同级 skill。
nano-banana- 连接/API(按图计费、MCP,以及 generate → upload to WoopSocial Media → attach
流程)→ 。
tools/integrations/ideogram.md - 提示词编写(本 skill)→ 指导如何恰当地生成所需素材。
- 路由器 → 根据任务选择工具。
image-prompt
本 skill 涵盖两种工作方式:下文的生成提示词编写,以及 Ideogram 应用内编辑器工作流(Canvas、Magic Fill、Extend、Style References、Magic Prompt、Layerize)—— 对于编辑器内操作,请参阅。每季度重新核验模型/规格。references/app-editor-and-canvas.md
Reach for Ideogram when… (match the job)
何时使用 Ideogram……(匹配任务)
Its real strengths: in-image text rendering (the standout — legible, correct typography),
deterministic layout (bounding-box placement), brand-accurate color (hex palettes), native
2K, and transparency (Background Remover). Reach elsewhere for conversational edits / pure
photoreal scenes (→ ) or specific art house looks (→ the photoreal branch). Don't
default it to every image. (Details: .)
nano-bananareferences/when-and-how-to-prompt.md它的真正优势:图像内文字渲染(最强项——字体排版清晰、准确)、
确定性布局(边界框定位)、符合品牌要求的标准色(十六进制色板)、原生
2K 和透明背景(Background Remover)。对于对话式编辑/纯照片写实场景
(→ )或特定的艺术风格(→ 照片写实分支),请选择其他工具。
不要默认用它处理所有图像。(详细信息:。)
nano-bananareferences/when-and-how-to-prompt.mdStep 0 — Read the brand + the job
第 0 步——读取品牌与任务
Load (palette as hex, type feel, do/don't). Identify the job (quote card /
carousel cover / poster / logo concept / ad / signage) and the aspect ratio (4:5, 9:16, 1:1).
brand-profile.md加载 (以十六进制表示的色板、字体调性、应做/不应做事项)。确定任务(语录卡片/
轮播封面/海报/logo 概念/广告/标牌)和宽高比(4:5、9:16、1:1)。
brand-profile.mdStep 1 — Direct a layout, not just a scene
第 1 步——引导布局,而不只是描述场景
Describe like a designer: subject/scene/style · text elements (exact string + styling + placement) ·
hex palette · layout/hierarchy · format (2K, aspect). Don't bury copy in a vague sentence. Ground in
the brand. See .
references/when-and-how-to-prompt.md像设计师一样描述:主体/场景/风格 · 文字元素(准确字符串 + 样式 + 位置)·
十六进制色板 · 布局/层级 · 格式(2K、宽高比)。不要把文案埋在含糊的句子中。
以品牌为依据。参见 。
references/when-and-how-to-prompt.mdStep 2 — Use the superpower: structured JSON
第 2 步——使用超级能力:结构化 JSON
Ideogram 4.0 is JSON-native. For exact, repeatable layout/text/color, write structured JSON:
per-element bounding boxes, hex palette (up to ~16), and each text element's **literal string
- visual styling**. Casual input works via magic-prompt (it expands to JSON). See
.
references/json-prompting-and-layout.md
Ideogram 4.0 原生支持 JSON。若要实现精确、可复现的布局/文字/颜色,请编写结构化 JSON:
为每个元素设置边界框,使用十六进制色板(最多约 16 种),并为每个文字元素提供**准确字符串
- 视觉样式**。普通输入可通过 magic-prompt 处理(它会扩展为 JSON)。参见
。
references/json-prompting-and-layout.md
Step 3 — Text, transparency, recipes
第 3 步——文字、透明背景与设计配方
- Text: ~0.97 OCR, multilingual, multi-line, logos/signage — but review every render.
- Transparency: Background Remover → clean alpha cutout. Layerize Text (live, beta) turns rendered text into editable layers — restyle/rewrite copy without regenerating; works best on clear, straight type. 2K output; aspect ratios in multiples of 16.
- Pick a recipe (quote card, carousel cover, logo concept, ad, poster). See
.
references/text-rendering-and-recipes.md
- 文字:约 0.97 的 OCR 准确率,支持多语言、多行、logo/标牌——但必须审查每次渲染结果。
- 透明背景:Background Remover → 干净的 alpha 抠图。Layerize Text(已上线,beta)可将 渲染后的文字转换为可编辑图层——无需重新生成即可调整样式/改写文案; 对于清晰、平直的文字效果最佳。2K 输出;宽高比为 16 的倍数。
- 选择一种配方(语录卡片、轮播封面、logo 概念、广告、海报)。参见
。
references/text-rendering-and-recipes.md
Step 4 — Iterate cheaply, then verify, disclose, ship
第 4 步——低成本迭代,然后核验、披露并发布
- Iterate on Turbo / magic-prompt to lock layout; finalize on Quality with refined JSON. Per-image pricing — prompt/layout precision is the cost + quality lever.
- Verify the rendered text and composition before publishing.
- Disclose AI images (EU AI Act Article 50, California AB 853) and sign with C2PA; never pass an AI image off as a real photo. Open weights are non-commercial (commercial → plan/API).
- Ship: generate per the integration guide → upload to WoopSocial Media → attach via
. WoopSocial doesn't generate images.
scheduling-and-queue
- 先在 Turbo / magic-prompt 上迭代以锁定布局;再用经过精炼的 JSON 在 Quality 模式下定稿。 按图计费——提示词/布局精度是控制成本与提升质量的关键杠杆。
- 发布前核验渲染后的文字与构图。
- 披露 AI 图像(EU AI Act Article 50、California AB 853),并添加 C2PA 签名; 绝不能把 AI 图像冒充真实照片。开放权重版本仅限非商业用途(商业用途 → 套餐/API)。
- **发布:**按照集成指南生成 → 上传至 WoopSocial Media → 通过
附加。WoopSocial 不生成图像。
scheduling-and-queue
Quality bar — self-check
质量标准——自检
- Did I match the tool to the job (route conversational/photoreal to )?
nano-banana - Are text elements typed (exact string + styling + placement), with a hex palette and 2K/ aspect set, brand-grounded?
- Did I use JSON where layout/text precision matters (and magic-prompt for casual)?
- Did I plan iterate-cheap → finalize, and verify the rendered text?
- Did I handle disclosure + C2PA, non-commercial license, and refuse real people / IP / logos?
- Did I point to for the API + WoopSocial flow (no claim WoopSocial generates images)?
tools/integrations/ideogram.md
- 是否匹配工具与任务(将对话式/照片写实需求路由至 )?
nano-banana - 是否明确写出了文字元素(准确字符串 + 样式 + 位置),是否设置了十六进制色板和 2K/ 宽高比,并以品牌为依据?
- 在需要精确控制布局/文字时是否使用了 JSON(普通需求使用 magic-prompt)?
- 是否规划了低成本迭代 → 定稿,并核验渲染后的文字?
- 是否处理了披露 + C2PA、非商业许可,并拒绝真实人物/IP/标志?
- 是否指向 以了解 API + WoopSocial 流程(且未声称 WoopSocial 会生成图像)?
tools/integrations/ideogram.md
Edge cases & pushback
边界情况与异议处理
- "Exact headline + brand colors + placement" → structured JSON (bounding boxes + hex palette).
- Conversational "now change the background" → route to ; Ideogram is layout-first.
nano-banana - Real person / copyrighted IP or logo / "post as a real photo" → refuse; disclose + C2PA; offer an original/owned alternative.
- "Editable text layers" → Layerize Text is live (beta, all plans + API endpoint**)** — best on clear, straight standard type; curved/decorative text may not be detected.
- "Generate it in WoopSocial" → WoopSocial doesn't generate; this prompts Ideogram, then the image is uploaded to Media and attached.
- Long paragraph of text in-image → keep lines short, hierarchy clear; verify the render.
- “准确标题 + 品牌色 + 位置” → 使用结构化 JSON(边界框 + 十六进制色板)。
- 对话式“现在更改背景” → 路由至 ;Ideogram 优先处理布局。
nano-banana - 真实人物/受版权保护的 IP 或 logo/“当作真实照片发布” → 拒绝;披露 + C2PA; 提供原创/已获授权的替代方案。
- “可编辑文字图层” → Layerize Text 已上线(beta,所有套餐 + API endpoint)—— 对于清晰、平直的标准字体效果最佳;弯曲/装饰性文字可能无法被检测到。
- “在 WoopSocial 中生成” → WoopSocial 不生成图像;本流程通过提示词驱动 Ideogram, 然后将图像上传到 Media 并附加。
- 图像中包含长段落文字 → 保持每行简短、层级清晰;核验渲染结果。
Related
相关内容
- — API/pricing/MCP, the upload-to-WoopSocial flow.
tools/integrations/ideogram.md - — the router;
image-prompt— the conversational/photoreal image sibling.nano-banana - — the visual brand;
brand-profile,carousel-writer,caption-writer— copy that pairs with the asset;hook-writer— animate a still into video (image-to-video).veo-3 - — attach the image to a post and publish.
scheduling-and-queue
- ——API/定价/MCP,以及上传至 WoopSocial 的流程。
tools/integrations/ideogram.md - ——路由器;
image-prompt——对话式/照片写实图像同级工具。nano-banana - ——视觉品牌;
brand-profile、carousel-writer、caption-writer——与素材配套的文案;hook-writer——将静态图像制作成视频(image-to-video)。veo-3 - ——将图像附加到帖子并发布。
scheduling-and-queue
References
参考资料
- — when to reach for Ideogram vs other tools, and the prompt anatomy.
references/when-and-how-to-prompt.md - — the 4.0 differentiator: structured JSON, bounding boxes, palettes.
references/json-prompting-and-layout.md - — the text superpower, transparency/2K, social recipes.
references/text-rendering-and-recipes.md - — the in-app editor workflow: Canvas, Magic Fill, Extend, Style References, Magic Prompt, brand models.
references/app-editor-and-canvas.md - — weak→strong, a JSON layout, a text-heavy card, and honest scope.
references/examples.md
- ——何时使用 Ideogram 与其他工具,以及提示词结构。
references/when-and-how-to-prompt.md - ——4.0 的差异化特性:结构化 JSON、边界框、色板。
references/json-prompting-and-layout.md - ——文字超级能力、透明背景/2K、社交媒体设计配方。
references/text-rendering-and-recipes.md - ——应用内编辑器工作流:Canvas、Magic Fill、Extend、Style References、Magic Prompt、品牌模型。
references/app-editor-and-canvas.md - ——从弱到强的示例、JSON 布局、文字密集型卡片,以及如实界定适用范围。
references/examples.md