--- title: "Generate a design from a text prompt with text detection and correction" method: POST path: "/v1/ideogram-v3/generate-design" tags: ["generate"] --- # Generate a design from a text prompt with text detection and correction `POST /v1/ideogram-v3/generate-design` Generates a design synchronously from a text prompt using the Ideogram 3.0 model, then detects and corrects text layers within the generated image. The response includes the generated image URL along with detected text layers (with font, size, color, position) and image asset layers. Images links are available for a limited period of time; if you would like to keep the image, you must download it. ## Request body - GenerateDesignRequestV3 - `prompt` string, required — The prompt to use to generate the design. - `seed` integer — Random seed. Set for reproducible generation. - `resolution` '512x1536' | '576x1408' | '576x1472' | '576x1536' | '640x1344' | '640x1408' | '640x1472' | '640x1536' | '704x1152' | '704x1216' | '704x1280' | '704x1344' | '704x1408' | '704x1472' | '736x1312' | '768x1088' | '768x1216' | '768x1280' | '768x1344' | '800x1280' | '832x960' | '832x1024' | '832x1088' | '832x1152' | '832x1216' | '832x1248' | '864x1152' | '896x960' | '896x1024' | '896x1088' | '896x1120' | '896x1152' | '960x832' | '960x896' | '960x1024' | '960x1088' | '1024x832' | '1024x896' | '1024x960' | '1024x1024' | '1088x768' | '1088x832' | '1088x896' | '1088x960' | '1120x896' | '1152x704' | '1152x832' | '1152x864' | '1152x896' | '1216x704' | '1216x768' | '1216x832' | '1248x832' | '1280x704' | '1280x768' | '1280x800' | '1312x736' | '1344x640' | '1344x704' | '1344x768' | '1408x576' | '1408x640' | '1408x704' | '1472x576' | '1472x640' | '1472x704' | '1536x512' | '1536x576' | '1536x640' — The resolutions supported for Ideogram 3.0. - `aspect_ratio` '1x3' | '3x1' | '1x2' | '2x1' | '9x16' | '16x9' | '10x16' | '16x10' | '2x3' | '3x2' | '3x4' | '4x3' | '4x5' | '5x4' | '1x1' — The aspect ratio to use for image generation, which determines the image's resolution. Cannot be used in conjunction with resolution. Defaults to 1x1. - `rendering_speed` 'FLASH' | 'TURBO' | 'BALANCED' | 'DEFAULT' | 'QUALITY' — The rendering speed to use. - `magic_prompt` 'AUTO' | 'ON' | 'OFF' — Determine if MagicPrompt should be used in generating the request or not. - `magic_prompt_system_prompt_config_id` string — A base64url-encoded magic prompt system prompt config ID to use for this request. - `negative_prompt` string — Description of what to exclude from a design. Descriptions in the prompt take precedence to descriptions in the negative prompt. - `num_images` integer — Number of designs to generate. - `color_palette` union — A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members). Not supported by V_1, V_1_TURBO, V_2A and V_2A_TURBO models. - ColorPaletteWithPresetName - `name` 'EMBER' | 'FRESH' | 'JUNGLE' | 'MAGIC' | 'MELON' | 'MOSAIC' | 'PASTEL' | 'ULTRAMARINE', required — A color palette preset value. - ColorPaletteWithMembers — A color palette represented only via its members. Cannot be used in conjunction with preset name. - `members` ColorPaletteMember[], required — A list of ColorPaletteMembers that define the color palette. Each color palette member consists of a required color hex and an optional weight between 0.05 and 1.0 (inclusive). It is recommended that these weights descend from highest to lowest for the color hexes provided. - `color_hex` string, required — The hexadecimal representation of the color with an optional chosen weight. - `color_weight` number — The weight of the color in the color palette. - `style_codes` StyleCode[] — A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style_type. - `style_type` 'AUTO' | 'GENERAL' | 'REALISTIC' | 'DESIGN' | 'CUSTOM' | 'FICTION' | 'STYLIZED' — The style type to generate with. - `style_preset` '80S_ILLUSTRATION' | '90S_NOSTALGIA' | 'ABSTRACT_ORGANIC' | 'ANALOG_NOSTALGIA' | 'ART_BRUT' | 'ART_DECO' | 'ART_POSTER' | 'AURA' | 'AVANT_GARDE' | 'BAUHAUS' | 'BLUEPRINT' | 'BLURRY_MOTION' | 'BRIGHT_ART' | 'C4D_CARTOON' | 'CHILDRENS_BOOK' | 'COLLAGE' | 'COLORING_BOOK_I' | 'COLORING_BOOK_II' | 'CUBISM' | 'DARK_AURA' | 'DOODLE' | 'DOUBLE_EXPOSURE' | 'DRAMATIC_CINEMA' | 'EDITORIAL' | 'EMOTIONAL_MINIMAL' | 'ETHEREAL_PARTY' | 'EXPIRED_FILM' | 'FLAT_ART' | 'FLAT_VECTOR' | 'FOREST_REVERIE' | 'GEO_MINIMALIST' | 'GLASS_PRISM' | 'GOLDEN_HOUR' | 'GRAFFITI_I' | 'GRAFFITI_II' | 'HALFTONE_PRINT' | 'HIGH_CONTRAST' | 'HIPPIE_ERA' | 'ICONIC' | 'JAPANDI_FUSION' | 'JAZZY' | 'LONG_EXPOSURE' | 'MAGAZINE_EDITORIAL' | 'MINIMAL_ILLUSTRATION' | 'MIXED_MEDIA' | 'MONOCHROME' | 'NIGHTLIFE' | 'OIL_PAINTING' | 'OLD_CARTOONS' | 'PAINT_GESTURE' | 'POP_ART' | 'RETRO_ETCHING' | 'RIVIERA_POP' | 'SPOTLIGHT_80S' | 'STYLIZED_RED' | 'SURREAL_COLLAGE' | 'TRAVEL_POSTER' | 'VINTAGE_GEO' | 'VINTAGE_POSTER' | 'WATERCOLOR' | 'WEIRD' | 'WOODBLOCK_PRINT' — A predefined style preset that applies a specific artistic style to the generated image. - `custom_model_uri` string — A custom model URI in the format model//version/. When provided, the model version and style will be resolved from this URI, and style_type is not required. - `font_file_h1` string, binary — Custom font file for H1 (heading) text. Supported formats .ttf, .otf, .woff, .woff2 (max 5MB). Takes priority over font_name_h1. - `font_name_h1` string — Font name from the available font library for H1 text. Ignored if font_file_h1 is provided. - `font_file_h2` string, binary — Custom font file for H2 (subheading) text. Supported formats .ttf, .otf, .woff, .woff2 (max 5MB). Takes priority over font_name_h2. - `font_name_h2` string — Font name from the available font library for H2 text. Ignored if font_file_h2 is provided. - `font_file_body` string, binary — Custom font file for body text. Supported formats .ttf, .otf, .woff, .woff2 (max 5MB). Takes priority over font_name_body. - `font_name_body` string — Font name from the available font library for body text. Ignored if font_file_body is provided. - `font_file_small` string, binary — Custom font file for small/caption text. Supported formats .ttf, .otf, .woff, .woff2 (max 5MB). Takes priority over font_name_small. - `font_name_small` string — Font name from the available font library for small text. Ignored if font_file_small is provided. - `style_reference_images` string[] — A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format. - `reference_asset_images` string[] — A set of asset images (e.g., logos, icons) to use as references for detection and replacement (maximum 10 images). The images should be in JPEG, PNG or WebP format. ## Response `200` Design(s) generated successfully with text correction. - LayeredImageGenerationResponseV3 — The response which contains information about the generated image, including the download link and other text layeres. Images links are available for a limited period of time; if you would like to keep the image, you must download it. - `response_type` 'layered' — Discriminator for the postGenerateDesignV4 oneOf response. Always "layered" for this shape; absent on the legacy postGenerateDesignV3 endpoint. - `created` string, date-time, required — The time the request was created. - `data` LayeredImageGenerationObjectV3[], required — A list of ImageObjects that contain the generated image(s). - `url` string, uri, nullable — The direct link to the image generated. - `prompt` string, required — The prompt used for the generation. This may be different from the original prompt. - `resolution` '512x1536' | '576x1408' | '576x1472' | '576x1536' | '640x1344' | '640x1408' | '640x1472' | '640x1536' | '704x1152' | '704x1216' | '704x1280' | '704x1344' | '704x1408' | '704x1472' | '736x1312' | '768x1088' | '768x1216' | '768x1280' | '768x1344' | '800x1280' | '832x960' | '832x1024' | '832x1088' | '832x1152' | '832x1216' | '832x1248' | '864x1152' | '896x960' | '896x1024' | '896x1088' | '896x1120' | '896x1152' | '960x832' | '960x896' | '960x1024' | '960x1088' | '1024x832' | '1024x896' | '1024x960' | '1024x1024' | '1088x768' | '1088x832' | '1088x896' | '1088x960' | '1120x896' | '1152x704' | '1152x832' | '1152x864' | '1152x896' | '1216x704' | '1216x768' | '1216x832' | '1248x832' | '1280x704' | '1280x768' | '1280x800' | '1312x736' | '1344x640' | '1344x704' | '1344x768' | '1408x576' | '1408x640' | '1408x704' | '1472x576' | '1472x640' | '1472x704' | '1536x512' | '1536x576' | '1536x640', required — The resolutions supported for Ideogram 3.0. - `upscaled_resolution` string — Output resolution, only used if operations alters image dimensions, such as upscale, crop etc. - `is_image_safe` boolean, required — Whether this request passes safety checks. If false, the url field will be empty. - `seed` integer, required — Random seed. Set for reproducible generation. - `style_type` 'AUTO' | 'GENERAL' | 'REALISTIC' | 'DESIGN' | 'CUSTOM' | 'FICTION' | 'STYLIZED' — The style type to generate with. ## Other responses - `400` — Invalid input provided. - `401` — Not authorized to generate an image. - `422` — Prompt failed the safety check. - `429` — Too many requests. --- [API](https://skmtc.net/ideogram/apis/ideogram-openapi-3-0.md) · [All operations](https://skmtc.net/ideogram/apis/ideogram-openapi-3-0/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/ideogram/ideogram-openapi-3-0/revisions/bd40f367a834/schema)