About Ideogram V4
Ideogram V4 (V4.0q) is a text-to-image model from Ideogram. It generates high-quality images, posters, and logos with crisp visuals, fine detail, and full creative control for polished, ready-to-use designs.
Typography and graphic design are Ideogram V4's strongest capabilities. It renders dense, accurate text that reads cleanly on posters, packaging, and brand work, including logos, multi-font layouts, long-form text, and creative typography integrated naturally into the design rather than pasted on top. The model was trained with bounding boxes tied to region descriptions, so it understands where every object, text region, and layout element belongs, enabling fine-grained control over composition.
Beyond design, Ideogram V4 delivers strong realism and broad artistic range. It renders in native 2K resolution with the fine texture and natural imperfections that separate a real photograph from an AI-generated image, supports native background transparency, and offers multiple quality tiers (Turbo, Balanced, Quality) so you can choose the right balance of speed and fidelity for drafts, iteration, or final output.
Ready to build with Ideogram V4?
Try Ideogram V4 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/images/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "ideogram-v4",
"prompt": "A red panda perched on a mossy branch in a misty forest at sunrise",
"image_size": "square_hd",
"rendering_speed": "BALANCED",
"expansion_model": "Medium",
"acceleration": "none",
"num_images": 1,
"enable_safety_checker": true,
"output_format": "jpeg"
}'Request parameters
Every field Ideogram V4 accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/images/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | The prompt to generate an image from. |
image_size | string | No | "square_hd" | The resolution of the generated image.square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9 |
rendering_speed | string | No | "BALANCED" | The rendering speed to use. Faster speeds use fewer denoising steps.TURBOBALANCEDQUALITY |
expansion_model | string | No | "Medium" | Which model expands the prompt. 'Medium' is fast; 'Large' uses Ideogram's Magic Prompt for the highest quality.MediumLarge |
acceleration | string | No | "none" | The acceleration level to use for the image generation.nonelowregularhigh |
num_images | integer | No | 1 | Number of images to generate. |
seed | integernullable | No | — | The seed to use for generation. If not provided, a random seed will be used. |
enable_safety_checker | boolean | No | true | If set to true, the safety checker will be enabled. |
output_format | string | No | "jpeg" | The format of the generated image.jpegpng |