RecraftMediumHigh

Recraft V3

Recraft V3 (code-named red_panda) is a text-to-image model with the ability to generate long texts, and images in a wide list of styles. SOTA in image generation per the Artificial Analysis Text-to-Image Benchmark.

93 credits

per image

State-of-the-art benchmark performance among text-to-image models

Long, accurate in-image text rendering

19 curated styles spanning realistic photography and digital illustration

15 fixed size presets in addition to aspect ratio control

Broad aspect ratio range from 1:2 to 2:1

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "recraft-ai/recraft-v3",
  "input": {
    "prompt": "a wildlife photography photo of a red panda using a laptop in a snowy forest",
    "size": "1365x1024",
    "style": "any"
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	-	Text prompt for image generation
`size`	string	No	1024x1024	Width and height of the generated image. Ignored if an aspect ratio is set 1024x10241365x10241024x13651536x10241024x15361820x10241024x18201024x20482048x10241434x10241024x14341024x12801280x10241024x17071707x1024
`style`	string	No	any	Style of the generated image (realistic photography or digital illustration variants) anyrealistic_imagedigital_illustrationdigital_illustration/pixel_artdigital_illustration/hand_drawndigital_illustration/graindigital_illustration/infantile_sketchdigital_illustration/2d_art_posterdigital_illustration/handmade_3ddigital_illustration/hand_drawn_outlinedigital_illustration/engraving_colordigital_illustration/2d_art_poster_2realistic_image/b_and_wrealistic_image/hard_flashrealistic_image/hdrrealistic_image/natural_lightrealistic_image/studio_portraitrealistic_image/enterpriserealistic_image/motion_blur
`aspect_ratio`	string	No	Not set	Aspect ratio of the generated image. Overrides size when set Not set1:14:33:43:22:316:99:161:22:17:55:74:55:43:55:3

Common Parameters

Common parameters used when calling POST /v1/predictions.

Parameter	Type	Required	Default	Description
`model`	string	Yes	-	Model identifier
`input`	object	Yes	-	Object containing the model-specific parameters from the table above
`output_folder`	string	No	-	Folder path for output files (max 256 chars, '..' not allowed)
`webhook_url`	string	No	-	Webhook URL to call on completion
`is_public`	boolean	No	false	If true, output files are also available via permanent public URLs

Examples

Wildlife Photography

A realistic wildlife photography style image

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "recraft-ai/recraft-v3",
  "input": {
    "prompt": "a wildlife photography photo of a red panda using a laptop in a snowy forest",
    "size": "1365x1024",
    "style": "any"
  }
}'