Image models

Ideogram V3

On this page

Operations
V3 Text To Image — ideogram-v3-text-to-image
V3 Edit — ideogram-v3-edit
V3 Remix — ideogram-v3-remix

Ideogram V3 — fast, high-fidelity AI image generation & editing.

modelId	ideogram-v3-text-to-image, ideogram-v3-edit, ideogram-v3-remix
Modality	image
Pricing	See this model on the Pricing page for the current per-call price (with your markup).

Operations

Operation	modelId	Endpoint	Required input
V3 Text To Image	ideogram-v3-text-to-image	POST /api/v1/generate	prompt
V3 Edit	ideogram-v3-edit	POST /api/v1/generate	prompt, image_url, mask_url
V3 Remix	ideogram-v3-remix	POST /api/v1/generate	prompt, image_url
Poll task	—	GET /api/v1/task/{id}?model=ideogram-v3-text-to-image	—

V3 Text To Image — ideogram-v3-text-to-image

Field	Type	Required	Values / example
prompt	string	Yes	Description of the image to generate Max 5000 characters. (default: Vintage travel poster of a mountain railway with the headline 'TAKE THE SLOW TRAIN' in art-deco lettering, dusk palette.)
rendering_speed	string	No	The rendering speed to use (options: TURBO \| BALANCED \| QUALITY) (default: BALANCED)
style	string	No	The style type to generate with. Cannot be used with style_codes. (options: AUTO \| GENERAL \| REALISTIC \| DESIGN) (default: AUTO)
expand_prompt	boolean	No	Determine if MagicPrompt should be used in generating the request or not (true/false) (default: true)
image_size	string	No	The resolution of the generated image (options: square \| square_hd \| portrait_4_3 \| portrait_16_9 \| landscape_4_3 \| landscape_16_9) (default: square_hd)
seed	number	No	Seed for the random number generator
negative_prompt	string	No	Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. Max 5000 characters.
nsfw_checker	boolean	No	A configurable parameter. Defaults to true in the Playground. (true/false) (default: true)

bash

curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"ideogram-v3-text-to-image","input":{"prompt":"A photorealistic portrait of a red fox in a snowy forest, soft morning light, shallow depth of field, 85mm.","rendering_speed":"BALANCED","style":"AUTO","expand_prompt":true,"image_size":"square_hd","seed":1,"negative_prompt":"blurry, low quality, distorted, watermark, text","nsfw_checker":true}}'

V3 Edit — ideogram-v3-edit

Field	Type	Required	Values / example
prompt	string	Yes	The prompt to fill the masked part of the image. Max 5000 characters. (default: Replace the pale sky with a dramatic sunset of coral and violet clouds, and spill warm amber light across the jagged mountain ridgeline so the peaks glow against the darkening valley.)
image_url	string	Yes	The image URL to generate an image from. Needs to match the dimensions of the mask. (image URL)
mask_url	string	Yes	Must be the SAME pixel dimensions as the input image, or the edit is rejected. (image URL)
rendering_speed	string	No	The rendering speed to use. Default value: "BALANCED" (options: TURBO \| BALANCED \| QUALITY) (default: BALANCED)
expand_prompt	boolean	No	Determine if MagicPrompt should be used in generating the request or not. Default value: true (true/false) (default: true)
seed	number	No	Seed for the random number generator
nsfw_checker	boolean	No	A configurable parameter. Defaults to true in the Playground. (true/false) (default: true)

bash

curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"ideogram-v3-edit","input":{"prompt":"A photorealistic portrait of a red fox in a snowy forest, soft morning light, shallow depth of field, 85mm.","image_url":"https://example.com/input.jpg","mask_url":"https://example.com/input.jpg","rendering_speed":"BALANCED","expand_prompt":true,"seed":1,"nsfw_checker":true}}'

V3 Remix — ideogram-v3-remix

Field	Type	Required	Values / example
prompt	string	Yes	The prompt to remix the image with Max 5000 characters. (default: Remix this street scene into a hand-painted travel poster with bold flat colors, an art-deco tram gliding through the foreground and a golden skyline rising behind it.)
image_url	string	Yes	The image URL to remix (image URL)
rendering_speed	string	No	The rendering speed to use (options: TURBO \| BALANCED \| QUALITY) (default: BALANCED)
style	string	No	The style type to generate with. Cannot be used with style_codes. (options: AUTO \| GENERAL \| REALISTIC \| DESIGN) (default: AUTO)
expand_prompt	boolean	No	Determine if MagicPrompt should be used in generating the request or not (true/false) (default: true)
image_size	string	No	The resolution of the generated image (options: square \| square_hd \| portrait_4_3 \| portrait_16_9 \| landscape_4_3 \| landscape_16_9) (default: square_hd)
num_images	string	No	Radio description (options: 1 \| 2 \| 3 \| 4) (default: 1)
seed	number	No	Seed for the random number generator
strength	number	No	Strength of the input image in the remix (range 0.01-1) (default: 0.8)
negative_prompt	string	No	Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. Max 5000 characters.
nsfw_checker	boolean	No	A configurable parameter. Defaults to true in the Playground. (true/false) (default: true)

bash

curl -X POST https://you.bot/api/v1/generate \
  -H "Authorization: Bearer $YOUBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"modelId":"ideogram-v3-remix","input":{"prompt":"A photorealistic portrait of a red fox in a snowy forest, soft morning light, shallow depth of field, 85mm.","image_url":"https://example.com/input.jpg","rendering_speed":"BALANCED","style":"AUTO","expand_prompt":true,"image_size":"square_hd","num_images":"1","seed":1,"strength":0.8,"negative_prompt":"blurry, low quality, distorted, watermark, text","nsfw_checker":true}}'

Ideogram Character Imagen 4