black-forest-labs/flux-kontext-dev-lora

FLUX.1 Kontext[dev] image editing model for running lora finetunes

Capabilities

Reference Images Seed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`input_image` *	string (uri)	Image to use as reference. Must be jpeg, png, gif, or webp.	`—`	—
`prompt` *	string	Text description of what you want to generate, or the instruction on how to edit the given image.	`—`	—
`aspect_ratio`	string	Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input 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 match_input_image
`disable_safety_checker`	boolean	Disable NSFW safety checker	`false`	—
`guidance`	number	Guidance scale for generation	`2.5`	min: 0, max: 10
`lora_strength`	number	Strength of the lora	`1`	—
`lora_weights`	string	Path to the lora weights	`—`	—
`megapixels`	string	Approximate number of megapixels for generated image	`"1"`	1 0.25
`num_inference_steps`	integer	Number of inference steps	`30`	min: 4, max: 50
`output_format`	string	Output image format	`"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
`seed`	integer	Random seed for reproducible generation. Leave blank for random.	`—`	—

input_image required string

Image to use as reference. Must be jpeg, png, gif, or webp.

prompt required string

Text description of what you want to generate, or the instruction on how to edit the given image.

aspect_ratio string

Aspect ratio of the generated image. Use 'match_input_image' to match the aspect ratio of the input 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 match_input_image

disable_safety_checker boolean

Disable NSFW safety checker

Default: false

guidance number

Guidance scale for generation

Default: 2.5 min: 0, max: 10

lora_strength number

Strength of the lora

Default: 1

lora_weights string

Path to the lora weights

megapixels string

Approximate number of megapixels for generated image

Default: "1"

1 0.25

num_inference_steps integer

Number of inference steps

Default: 30 min: 4, max: 50

output_format string

Output image format

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

seed integer

Random seed for reproducible generation. Leave blank for random.

Version: 50c10b8f14af Updated: 6/26/2026 265.5K runs