Ideogram AI Ideogram V3 Turbo
Playground
Try it on WaveSpeedAI!Ideogram V3 Turbo produces the highest-quality Ideogram v3 images with photorealistic detail, creative designs, and consistent style. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Features
Generate stunning images with exceptional typography using Ideogram V3 Turbo. This versatile model excels at rendering text within images — perfect for posters, logos, marketing materials, and design work. With support for image editing, mask-based inpainting, and up to 3 reference images, it’s a complete creative toolkit.
Why It Looks Great
- Superior typography: Industry-leading text rendering for posters, logos, and designs.
- Multiple modes: Text-to-image generation, image editing, and masked inpainting.
- Style presets: Choose from Auto, General, Realistic, or Design styles.
- Reference images: Use up to 3 reference images to guide generation.
- Mask support: Precise regional editing with custom masks.
- Flexible aspect ratios: Five format options for any use case.
- Safety Checker: Optional content filtering for appropriate output.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the image you want to generate. |
| image | No | Source image for editing (upload or public URL). |
| mask_image | No | Mask to specify edit regions — white areas will be regenerated. |
| style | No | Output style: Auto, General, Realistic, or Design. Default: Auto. |
| aspect_ratio | No | Output format: 1:1, 16:9, 9:16, 4:3, or 3:4. Default: 1:1. |
| reference_images | No | Up to 3 reference images to guide style and composition. |
| enable_base64_output | No | API only: Returns base64 string instead of URL. |
| Enable Safety Checker | No | Toggle content safety filtering. |
How to Use
Text-to-Image Generation
- Write your prompt — describe the image including any text you want rendered.
- Choose style — select Auto, General, Realistic, or Design.
- Set aspect ratio — pick the format that fits your use case.
- Add reference images (optional) — click ”+ Add Item” to include style references.
- Run — click the button to generate.
- Download — preview and save your image.
Image Editing
- Upload source image — the image you want to edit.
- Upload mask (optional) — white areas indicate regions to regenerate.
- Write your prompt — describe the desired changes or new elements.
- Run — click the button to apply edits.
Pricing
Flat rate per image generation.
| Output | Cost |
|---|---|
| Per image | $0.03 |
Style Guide
| Style | Description | Best For |
|---|---|---|
| Auto | Automatically selects the best style | General use, when unsure |
| General | Balanced, versatile output | Wide range of subjects |
| Realistic | Photorealistic, natural appearance | Photos, portraits, products |
| Design | Graphic design aesthetic | Posters, logos, marketing materials |
Best Use Cases
- Typography & Posters — Create designs with perfectly rendered text and lettering.
- Logo Design — Generate logo concepts with clean, readable text.
- Marketing Materials — Produce banners, ads, and promotional graphics.
- Social Media Graphics — Design eye-catching posts with integrated text.
- Product Mockups — Visualize packaging and branded materials.
Example Prompts
- “beautiful bauhaus stark typographic poster saying ‘Ideogram v3 turbo on WaveSpeedAI’, pink and yellow”
- “minimalist logo design for a coffee shop called ‘Morning Brew’, earth tones, clean typography”
- “movie poster for a sci-fi film titled ‘NEXUS’, dramatic lighting, futuristic cityscape”
- “Instagram story template with text ‘SALE 50% OFF’, bold modern typography, gradient background”
- “vintage travel poster for Tokyo, retro illustration style, Japanese text integration”
Reference Images Tips
| Number of References | Best Use Case |
|---|---|
| 0 | Pure generation from prompt |
| 1 | Match a specific style or composition |
| 2-3 | Combine multiple style elements or ensure consistency |
Pro Tips for Best Results
- For typography, put the exact text in quotes within your prompt.
- Use the Design style for graphic design work with text elements.
- Realistic style works best for photographic content without heavy text.
- Reference images help maintain consistency across multiple generations.
- Use masks to selectively edit only specific areas of an image.
- Describe typography style: “bold”, “minimalist”, “vintage”, “modern”, “serif”, “sans-serif”.
Notes
- Ideogram is renowned for best-in-class text rendering in AI-generated images.
- If using URLs for images, ensure they are publicly accessible.
- The enable_base64_output option is only available through the API.
- Enable Safety Checker for content that will be publicly shared.
- Reference images (up to 3) help guide style without directly copying content.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"style": "Auto",
"aspect_ratio": "1:1"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/ideogram-ai/ideogram-v3-turbo" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}")
RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The positive prompt for the generation. | |
| image | string | No | - | The image to generate an image from. | |
| mask_image | string | No | - | The mask image tells the model where to generate new pixels (white) and where to preserve the original image (black). It acts as a stencil or guide for targeted image editing. | |
| style | string | No | Auto | Auto, General, Realistic, Design | The style of the generated image. |
| aspect_ratio | string | No | 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4 | The aspect ratio of the generated media. |
| reference_images | array<string> | No | - | 0 ~ 3 items | A list of images to use as style references. |
| enable_base64_output | boolean | No | false | - | If set to `true`, the prediction's `output` strings are returned as **naked base64** (no `data:<mime>;base64,` prefix). When `false` (default), outputs are returned as URLs pointing to our CDN. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |