black-forest-labs/flux-krea-dev

Official View on Replicate →

An opinionated text-to-image model from Black Forest Labs in collaboration with Krea that excels in photorealism. Creates images that avoid the oversaturated "AI look".

Capabilities

Reference Images Seed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`prompt` *	string	Prompt for generated image	`—`	—
`aspect_ratio`	string	Aspect ratio for the generated image	`"1:1"`	1:1 16:9 21:9 3:2 2:3 4:5 5:4 3:4 4:3 9:16 9:21
`disable_safety_checker`	boolean	Disable safety checker for generated images.	`false`	—
`go_fast`	boolean	Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16. Note that outputs will not be deterministic when this is enabled, even if you set a seed.	`true`	—
`guidance`	number	Guidance for generated image	`3`	min: 0, max: 10
`image`	string (uri)	Input image for image to image mode. The aspect ratio of your output will match this image	`—`	—
`megapixels`	string	Approximate number of megapixels for generated image	`"1"`	1 0.25
`num_inference_steps`	integer	Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.	`28`	min: 1, max: 50
`num_outputs`	integer	Number of outputs to generate	`1`	min: 1, max: 4
`output_format`	string	Format of the output images	`"webp"`	webp jpg png
`output_quality`	integer	Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs	`80`	min: 0, max: 100
`prompt_strength`	number	Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image	`0.8`	min: 0, max: 1
`seed`	integer	Random seed. Set for reproducible generation	`—`	—

prompt required string

Prompt for generated image

aspect_ratio string

Aspect ratio for the generated image

Default: "1:1"

1:1 16:9 21:9 3:2 2:3 4:5 5:4 3:4 4:3 9:16 9:21

disable_safety_checker boolean

Disable safety checker for generated images.

Default: false

go_fast boolean

Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16. Note that outputs will not be deterministic when this is enabled, even if you set a seed.

Default: true

guidance number

Guidance for generated image

Default: 3 min: 0, max: 10

image string

Input image for image to image mode. The aspect ratio of your output will match this image

megapixels string

Approximate number of megapixels for generated image

Default: "1"

1 0.25

num_inference_steps integer

Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.

Default: 28 min: 1, max: 50

num_outputs integer

Number of outputs to generate

Default: 1 min: 1, max: 4

output_format string

Format of the output images

Default: "webp"

webp jpg png

output_quality integer

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80 min: 0, max: 100

prompt_strength number

Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image

Default: 0.8 min: 0, max: 1

seed integer

Random seed. Set for reproducible generation

Version: 9d7a7c510de5 Updated: 6/26/2026 3.0M runs