ABOUT THE WORKFLOW

Generate an Image from Text
Write a prompt describing the image you want. Ideogram V4 generates it with near-perfect text rendering, strong layout control, and native high resolution. Put any words you want inside the image in quotes within your prompt and they render legibly, even across multiple text regions, languages, and font sizes. Pick your aspect ratio, rendering speed, and output format, then download.

Partner node. This workflow calls an external API, so each run uses credits from your API wallet. No API key needed. Floyo handles the connection.

Model

• Ideogram V4 (4.0) by Ideogram AI. A 9.3-billion-parameter Diffusion Transformer and the highest-ranked open-weight image model on Arena.ai. Scores 0.97 OCR accuracy on in-image text rendering, ahead of every other open-weight model at any parameter scale. Supports bounding-box layout control, structured JSON prompting, multilingual typography, and native 2K output.

HOW IT WORKS

Step 1. Write your prompt
Describe the image: subject, setting, style, lighting, composition. To add text inside the image, put the exact words in quotes. "A neon sign reading 'OPEN LATE' above a rain-soaked bar entrance, cinematic night photography, reflections on wet pavement" tells the model both what to show and what to write.
Works great with: posters · packaging · signage · social graphics · product mockups · editorial photography

Step 2. Choose your aspect ratio
Pick the shape that fits your output: 16:9 landscape for widescreen, 9:16 portrait for vertical, 1:1 square for social, or other presets for print and web formats.

Step 3. Choose your rendering speed
Turbo is fastest, Balanced is the default trade-off, Quality is slowest with the most detail. Start with Balanced.

Step 4. Hit run and download
Ideogram V4 generates the image and returns it in your chosen format (JPEG or PNG).
Ready for: Figma · Photoshop · Canva · print · social media · web

First time? Leave every setting as-is. The defaults (16:9 landscape, Balanced speed, 1 image, JPEG) are the right starting point for almost everyone.

RECOMMENDED SETTINGS

Quick-start guide. Find the goal that matches yours and copy the settings.

• Standard image generation (most people) — 16:9 landscape, Balanced speed, 1 image, random seed. No changes needed.

• Highest quality output — Switch rendering speed to Quality. Slower, but produces the most detailed and refined result. Use for final deliverables and print.

• Fast drafts and iteration — Switch to Turbo. Quickest render, good for testing prompts and exploring compositions before committing to a Quality run.

• Text-heavy designs — Put every word you want in the image inside quotes in the prompt. Ideogram V4 handles multiple text regions, different font sizes, and multilingual copy in a single image. "A poster reading 'SUMMER SALE' at the top and '50% OFF' at the bottom" gives it clear placement cues.

• Specific layout control — Ideogram V4 supports bounding-box layout instructions. Describe where elements should go: "logo top-left, headline centered, product image bottom-right."

• Multiple variations — Raise the number of images to generate several versions per run. Compare compositions and text placement, then pick the strongest.

• Need a different format — Switch output from JPEG to PNG if you need transparency support or lossless quality.

Prompt: For design work, describe the layout and text placement alongside the visual content. "A vintage travel poster for Tokyo, bold headline reading 'TOKYO' at the top, cherry blossoms framing Mount Fuji, warm retro color palette, screenprint texture" tells the model what to draw, what to write, and where to put it. For photographic work, use camera and lens language as usual.

LEARN

📹 Videos

• Intro to Floyo

• ComfyUI 101 Free Course ft. Sebastian Kamph

• Floyo 101 for Team Collaboration

✨ Quick links

• Help docs

• LoRA Training guide

• Discover more workflows

USE CASES

🪧 Posters, Signage, and Print Design
Generate complete poster layouts, event flyers, or signage with readable headlines, subheads, and body text in a single pass. No post-production text overlay needed.

📦 Packaging and Product Mockups
Create product packaging concepts with accurate brand names, taglines, and label copy rendered directly in the image, including multilingual text.

📱 Social Media Graphics
Generate scroll-ready social posts with overlay text, hashtags, and call-to-action copy baked into the image. Choose the aspect ratio to match the platform.

📸 Editorial and Commercial Photography
Generate photorealistic scenes with cinematic lighting, depth of field, and composition control for mood boards, pitch decks, and ad concepts.

🌐 Multilingual Design
Render text in multiple languages within the same image. Ideogram V4 handles Latin, CJK, and accented characters with consistent accuracy and alignment.

WHAT WORKS BEST / WHAT TO AVOID

✅ Works great

• Text in quotes within the prompt for accurate in-image rendering

• Layout descriptions with spatial cues (top, center, bottom-right)

• Design-oriented prompts (posters, packaging, signage, social graphics)

• Photographic prompts with camera, lens, and lighting language

⚠️ May produce softer results

• Very long blocks of text (8+ lines) without clear layout direction

• Extremely small font sizes in complex scenes

• Prompts with no spatial or compositional guidance

• Mixing too many unrelated text regions in one image

FAQ

What is Ideogram V4?
Ideogram V4 (4.0) is a 9.3-billion-parameter text-to-image model by Ideogram AI, released June 2026. It is the highest-ranked open-weight image model on Arena.ai and the top-performing model for in-image text rendering, scoring 0.97 on English OCR accuracy benchmarks. It generates at native 2K resolution and supports structured JSON prompting, bounding-box layout control, and multilingual typography.

How good is the text rendering compared to other models?
Ideogram V4 leads all open-weight models in text rendering accuracy and outperforms most closed models as well. It handles multiple text regions, different font sizes, accented characters, and multilingual copy within a single image. Where models like Flux and Stable Diffusion frequently garble or drop characters, Ideogram V4 renders them cleanly and consistently.

What does rendering speed do?
Rendering speed controls the trade-off between generation time and image quality. Turbo is the fastest with slightly less refinement. Balanced is the default middle ground. Quality is the slowest but produces the most detailed, polished output. Start with Balanced and switch to Quality for final deliverables.

Can I control where elements appear in the image?
Yes. Ideogram V4 supports layout control through spatial descriptions in the prompt ("headline at the top, product centered, tagline bottom-left") and through structured JSON prompting with bounding-box coordinates for precise element placement.

Does Ideogram V4 support multiple languages in one image?
Yes. It renders Latin-script languages, CJK characters, and accented text accurately within the same image. This makes it suitable for bilingual packaging, multilingual signage, and international marketing materials.

Is Ideogram V4 licensed for commercial use?
Yes. Ideogram V4 is released as open-weight with a commercial license. You can use generated images for commercial projects including advertising, packaging, product design, and client work. Review the full license terms on the Ideogram model page for your specific use case.

How to run Ideogram V4 online?
You can run Ideogram V4 online through Floyo. No installation, no setup, no API key to wire up. Open the workflow in your browser, write your prompt, and hit run. Free to try.

WHY FLOYO?

Floyo is the only platform with team collaboration for ComfyUI in the browser. You run workflows with no install. You share run history, assets, and models across your team. You pay only when you generate. Floyo supports open-source and closed-source models.

A designer runs an edit and likes the result. A teammate opens that exact run from shared history and keeps going. No file handoffs. No version confusion.

For studios and enterprise teams, Floyo adds private workspaces, pooled resources, and a team usage dashboard. Other ComfyUI cloud tools run for one person at a time. Floyo runs for the whole team, with transparent per-generation costs.

Ready to try it?
Write your prompt, put any in-image text in quotes, and hit run.

→ Launch Workflow, Free

Questions? Watch the free course or check the FAQ above.