ideogram-core-workflow-a
Execute Ideogram primary workflow: Core Workflow A. Use when implementing primary use case, building main features, or core integration tasks. Trigger with phrases like "ideogram main workflow", "primary task with ideogram".
Install
mkdir -p .claude/skills/ideogram-core-workflow-a && curl -L -o skill.zip "https://mcp.directory/api/skills/download/8859" && unzip -o skill.zip -d .claude/skills/ideogram-core-workflow-a && rm skill.zipInstalls to .claude/skills/ideogram-core-workflow-a
About this skill
Ideogram Core Workflow A -- Text-to-Image Generation
Overview
Primary workflow for Ideogram: generating images from text prompts. Ideogram excels at rendering legible text inside images -- a capability where most image models fail. Use this for social media graphics, marketing banners, product mockups, posters, logos, and any visual that combines illustration with typography.
Prerequisites
- Completed
ideogram-install-authsetup IDEOGRAM_API_KEYenvironment variable set- Understanding of style types and aspect ratios
Instructions
Step 1: Choose Parameters for Your Use Case
| Use Case | Style Type | Aspect Ratio | Model | Notes |
|---|---|---|---|---|
| Social media post | DESIGN | ASPECT_1_1 | V_2 | Best text rendering |
| Blog hero image | REALISTIC | ASPECT_16_9 | V_2 | Photorealistic |
| Story / Reel | GENERAL | ASPECT_9_16 | V_2_TURBO | Fast, vertical |
| Logo / Icon | DESIGN | ASPECT_1_1 | V_2 | Clean typography |
| Product mockup | REALISTIC | ASPECT_4_3 | V_2 | Studio quality |
| Anime illustration | ANIME | ASPECT_3_4 | V_2 | Japanese art style |
| 3D render | RENDER_3D | ASPECT_16_9 | V_2 | 3D scene |
| Wide banner | DESIGN | ASPECT_3_1 | V_2 | Website header |
Step 2: Generate Image (Legacy Endpoint)
import { writeFileSync, mkdirSync } from "fs";
async function generateImage(prompt: string, options: {
model?: string;
style_type?: string;
aspect_ratio?: string;
negative_prompt?: string;
seed?: number;
} = {}) {
const response = await fetch("https://api.ideogram.ai/generate", {
method: "POST",
headers: {
"Api-Key": process.env.IDEOGRAM_API_KEY!,
"Content-Type": "application/json",
},
body: JSON.stringify({
image_request: {
prompt,
model: options.model ?? "V_2",
style_type: options.style_type ?? "DESIGN",
aspect_ratio: options.aspect_ratio ?? "ASPECT_1_1",
magic_prompt_option: "AUTO",
negative_prompt: options.negative_prompt,
seed: options.seed,
num_images: 1,
},
}),
});
if (!response.ok) {
const err = await response.text();
throw new Error(`Generation failed (${response.status}): ${err}`);
}
const result = await response.json();
const image = result.data[0];
// Download immediately -- URLs expire after ~1 hour
const imgResp = await fetch(image.url);
const buffer = Buffer.from(await imgResp.arrayBuffer());
mkdirSync("./output", { recursive: true });
const filename = `ideogram-${image.seed}.png`;
writeFileSync(`./output/${filename}`, buffer);
return { ...image, localPath: `./output/${filename}` };
}
Step 3: Generate with V3 Endpoint (Multipart)
async function generateV3(prompt: string, options: {
aspect_ratio?: string;
style_type?: string;
rendering_speed?: string;
negative_prompt?: string;
magic_prompt?: string;
style_preset?: string;
} = {}) {
const form = new FormData();
form.append("prompt", prompt);
form.append("aspect_ratio", options.aspect_ratio ?? "1x1");
form.append("style_type", options.style_type ?? "DESIGN");
form.append("rendering_speed", options.rendering_speed ?? "DEFAULT");
form.append("magic_prompt", options.magic_prompt ?? "AUTO");
if (options.negative_prompt) form.append("negative_prompt", options.negative_prompt);
if (options.style_preset) form.append("style_preset", options.style_preset);
const response = await fetch("https://api.ideogram.ai/v1/ideogram-v3/generate", {
method: "POST",
headers: { "Api-Key": process.env.IDEOGRAM_API_KEY! },
body: form,
});
if (!response.ok) throw new Error(`V3 generation failed: ${response.status}`);
return response.json();
}
Step 4: Text-in-Image Best Practices
// Ideogram renders quoted text literally inside the image
const textPrompts = [
// Enclose desired text in quotes within the prompt
'A coffee shop chalkboard menu with text "DAILY SPECIALS" and "Latte $4.50"',
'A retro neon sign glowing with the words "OPEN 24 HOURS"',
'Professional business card design with "Jane Smith" and "CEO" text',
'Birthday card with elegant gold script "Happy Birthday!"',
];
// Use DESIGN style for best text accuracy
for (const prompt of textPrompts) {
const result = await generateImage(prompt, {
style_type: "DESIGN",
negative_prompt: "blurry text, misspelled, distorted letters",
});
console.log(`Generated: ${result.localPath} (seed: ${result.seed})`);
}
Step 5: Batch Generation with Seed Consistency
// Use the same seed to reproduce or create consistent variations
async function generateVariations(basePrompt: string, seed: number) {
const variations = [
{ suffix: ", minimalist style", style: "DESIGN" },
{ suffix: ", photorealistic", style: "REALISTIC" },
{ suffix: ", anime style", style: "ANIME" },
];
const results = [];
for (const v of variations) {
const result = await generateImage(`${basePrompt}${v.suffix}`, {
style_type: v.style,
seed,
});
results.push(result);
await new Promise(r => setTimeout(r, 3000)); // Rate limit courtesy
}
return results;
}
V3 Style Presets (50+)
80S_ILLUSTRATION, 90S_NOSTALGIA, ART_DECO, ART_POSTER, BAUHAUS, BLUEPRINT, BRIGHT_ART, CHILDRENS_BOOK, COLLAGE, CUBISM, DOUBLE_EXPOSURE, DRAMATIC_CINEMA, EDITORIAL, FLAT_ART, FLAT_VECTOR, GOLDEN_HOUR, GRAFFITI_I, HALFTONE_PRINT, JAPANDI_FUSION, LONG_EXPOSURE, MAGAZINE_EDITORIAL, MIXED_MEDIA, MONOCHROME, OIL_PAINTING, POP_ART, RETRO_ETCHING, SURREAL_COLLAGE, TRAVEL_POSTER, VINTAGE_POSTER, WATERCOLOR, and more.
V3 Rendering Speeds
| Speed | Quality | Cost | Use Case |
|---|---|---|---|
FLASH | Lowest | Cheapest | Quick previews |
TURBO | Good | Low | Drafts, iteration |
DEFAULT | High | Standard | Production assets |
QUALITY | Highest | Premium | Final deliverables |
Error Handling
| Error | HTTP Status | Cause | Solution |
|---|---|---|---|
| Content filtered | 422 | Prompt failed safety check | Remove brand names, trademarks, or flagged terms |
| Bad aspect ratio | 400 | Invalid enum value | Use exact enum values (e.g., ASPECT_16_9 not 16:9) |
| Rate limited | 429 | 10+ in-flight requests | Queue with 3s delays between calls |
| Expired URL | -- | Downloaded too late | Fetch image within minutes of generation |
Output
- Generated image files downloaded to
./output/ - Metadata: URL, seed, resolution, style type, safety status
- Seed values logged for reproducibility
Resources
Next Steps
For editing and remixing, see ideogram-core-workflow-b.
More by jeremylongshore
View all skills by jeremylongshore →You might also like
flutter-development
aj-geddes
Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.
drawio-diagrams-enhanced
jgtolentino
Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.
ui-ux-pro-max
nextlevelbuilder
"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."
godot
bfollington
This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.
nano-banana-pro
garg-aayush
Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.
pdf-to-markdown
aliceisjustplaying
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Related MCP Servers
Browse all serversConnect Blender to Claude AI for seamless 3D modeling. Use AI 3D model generator tools for faster, intuitive, interactiv
AIPo Labs — dynamic search and execute any tools available on ACI.dev for fast, flexible AI-powered workflows.
TaskManager streamlines project tracking and time management with efficient task queues, ideal for managing projects sof
Access mac keyboard shortcuts for screen capture and automate workflows with Siri Shortcuts. Streamline hotkey screensho
Integrate with Salesforce CRM to manage records, execute queries, and automate workflows using natural language interact
Easily interact with MySQL databases: execute queries, manage connections, and streamline your data workflow using MySQL
Stay ahead of the MCP ecosystem
Get weekly updates on new skills and servers.