Vidu Contest
WaveSpeed.ai
Beranda/Jelajahi/Ideogram Image Models/ideogram-ai/ideogram-v2-turbo
text-to-image

text-to-image

Ideogram V2 Turbo

ideogram-ai/ideogram-v2-turbo

Ideogram v2 turbo is an image model that excels at inpainting, prompt comprehension, and accurate on-image text rendering. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Input

Hint: You can drag and drop a file or click to upload

Hint: You can drag and drop a file or click to upload

If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

A beautiful typographic poster with the text "Run Ideogram on WaveSpeedAI", against an epic space scene

Permintaan Anda akan membutuhkan $0.05 per run.

Untuk $1 Anda dapat menjalankan model ini sekitar 20 kali.

Satu lagi hal:

ContohLihat semua

A beautiful typographic poster with the text "Run Ideogram on WaveSpeedAI", against an epic space scene
A beautiful typographic poster with the text "Run Ideogram on WaveSpeedAI", against an epic space scene
Young man sitting alone in a dimly lit room with window blinds casting shadows on his face, contemplative expression, detailed emotion, cinematic noir style
Woman in a flowing dress dancing in a swirl of paint and color, abstract brush strokes, expressive movement, vibrant tones, artistic composition
Portrait of a man whose face is morphing into geometric shapes and fractals, modern art inspired, clean color contrast, crisp and high-resolution details
Space explorer removing helmet on an alien planet, galaxy sky background, reflective suit, high-tech interface overlay, intense lighting and detail
A vibrant and delicious-looking flat lay photo for a food blog. A rustic ceramic bowl is filled with a colorful quinoa salad, topped with avocado slices, cherry tomatoes, and feta cheese. Around the bowl are fresh ingredients like a lemon and a sprig of cilantro. The title 'WavespeedAI' is written on a piece of parchment paper next to the bowl. photo, food photography, top-down view, bright and airy.
A candid photograph of a young woman in her early 20s sitting in a cozy, sun-drenched coffee shop. She has a natural, gentle smile as she looks out the window. She is wearing a simple knitted sweater. Soft morning light illuminates the fine details of her face, including light freckles across her nose. Shot on a 50mm f/1.4 lens, shallow depth of field, photorealistic.
A close-up photograph of a 6-year-old girl with bright, curious eyes, laughing heartily. She has messy blonde hair with a few wildflowers tucked into it. The photo is taken outdoors during the golden hour, with warm, golden sunlight backlighting her hair, creating a beautiful halo effect. Extremely detailed, sharp focus on her eyes, joyful, photorealistic.
An environmental portrait of a university professor in his 50s, sitting in a classic, grand library surrounded by old books. He is wearing tweed jacket and glasses, looking thoughtfully at a book in his hands. The room is filled with warm, ambient light from desk lamps. The atmosphere is quiet and intellectual. Photograph, cinematic, realistic.

README

Ideogram V2 Turbo

Ideogram V2 Turbo is a powerful text-to-image generation model renowned for its exceptional ability to render text within images. Generate stunning visuals with accurate, readable text — perfect for posters, logos, typography, and designs that require precise text integration.

Why It Stands Out

  • Superior text rendering: Industry-leading accuracy for generating readable text within images.
  • Multi-mode support: Works as text-to-image, image-to-image, and inpainting generator.
  • Prompt Enhancer: Built-in AI-powered prompt optimization for better results.
  • Style presets: Choose from various style options or let the model decide with Auto.
  • Flexible aspect ratios: Multiple aspect ratio presets for different use cases.
  • Inpainting support: Use mask images for precise, targeted image editing.

Parameters

ParameterRequiredDescription
promptYesText description of the image you want to generate.
imageNoSource image for image-to-image transformation.
mask_imageNoMask for inpainting (white = generate, black = preserve).
styleNoStyle preset: Auto or specific styles (default: Auto).
aspect_ratioNoOutput aspect ratio: 16:9, 1:1, 9:16, etc. (default: 16:9).
enable_base64_outputNoReturn base64 string instead of URL (API only).

How to Use

Text-to-Image:

  1. Write a prompt describing the image you want. Use the Prompt Enhancer for AI-assisted optimization.
  2. Select a style preset or use Auto.
  3. Choose your desired aspect ratio.
  4. Click Run and download your image.

Image-to-Image:

  1. Upload a source image.
  2. Write a prompt describing the transformation.
  3. Adjust style and aspect ratio as needed.
  4. Click Run and download your image.

Inpainting:

  1. Upload a source image and a mask image.
  2. White areas in the mask will be regenerated based on your prompt.
  3. Write a prompt describing what should appear in the masked region.
  4. Click Run and download your image.

Best Use Cases

  • Typography & Posters — Create posters, banners, and designs with accurate, stylized text.
  • Logo Design — Generate logo concepts with readable brand names.
  • Social Media Graphics — Produce text-heavy visuals for posts and ads.
  • Marketing Materials — Create promotional images with integrated messaging.
  • Signage & Mockups — Generate realistic signs, storefronts, and product labels.
  • Memes & Content — Create images with embedded text for entertainment.

Pricing

OutputPrice
Per image$0.05

Pro Tips for Best Quality

  • For text rendering, include the exact text in quotes within your prompt.
  • Specify font style if desired (e.g., "bold sans-serif," "elegant script," "neon sign").
  • Use the inpainting feature with masks to edit specific areas while preserving the rest.
  • Choose an appropriate style preset to match your creative vision.
  • Select the right aspect ratio for your intended use (16:9 for banners, 9:16 for mobile, etc.).

Notes

  • Ensure uploaded image URLs are publicly accessible.
  • Processing time varies based on current queue load.
  • Please ensure your prompts comply with content guidelines.

Features

https://docs.ideogram.ai/using-ideogram/ideogram-features