Krea AIMediumHigh

FLUX.1 Krea [dev]

Photorealistic image generation that specifically avoids the 'AI look', producing natural-looking images indistinguishable from real photographs.

45 credits

per image

Photorealistic output without AI artifacts

Natural-looking image generation

Avoids typical AI aesthetic tells

High-quality texture and detail

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.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": "black-forest-labs/flux-krea-dev",
  "input": {
    "prompt": "Candid photograph of a barista making latte art in a cozy coffee shop, natural window lighting, shot on Canon EOS R5, shallow depth of field",
    "image_size": "portrait_4_3",
    "num_inference_steps": 28,
    "guidance_scale": 3.5
  }
}'

Parameters

Parameter	Type	Required	Default	Description
`prompt`	string	Yes	-	Text description of the image to generate
`image`	string	No	-	Input image URL for image-to-image mode
`aspect_ratio`	string	No	1:1	Aspect ratio for the generated image 1:116:99:164:33:43:22:3
`num_outputs`	integer	No	1	Number of outputs to generate
`num_inference_steps`	integer	No	28	Number of denoising steps (recommended: 28-50)
`guidance`	number	No	3	Guidance for generated image (lower values = more realistic, good values: 2, 2.5, 3, 3.5)
`seed`	integer	No	-	Random seed for reproducibility
`go_fast`	boolean	No	-	Run faster predictions with additional optimizations
`output_format`	string	No	webp	Format of the output images pngjpgwebp
`output_quality`	integer	No	80	Quality of output images (0-100)
`megapixels`	string	No	1	Approximate megapixels for output

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

Natural Portrait

Generate a photorealistic portrait without AI look

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "black-forest-labs/flux-krea-dev",
  "input": {
    "prompt": "Candid photograph of a barista making latte art in a cozy coffee shop, natural window lighting, shot on Canon EOS R5, shallow depth of field",
    "image_size": "portrait_4_3",
    "num_inference_steps": 28,
    "guidance_scale": 3.5
  }
}'