prunaai/flux-kontext-fast

Ultra fast flux kontext endpoint

Capabilities

Seed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`img_cond_path` *	string (uri)	Input image for image to image mode. The aspect ratio of your output will match this image	`—`	—
`prompt` *	string	Prompt	`—`	—
`aspect_ratio`	string	Aspect ratio of the output image	`"match_input_image"`	match_input_image 1:1 16:9 21:9 3:2 2:3 4:5 5:4 3:4 4:3 9:16 9:21
`guidance`	number	Guidance scale	`3.5`	—
`image_size`	integer	Base image size (longest side)	`1024`	—
`num_inference_steps`	integer	Number of inference steps	`30`	—
`output_format`	string	Output format	`"jpg"`	png jpg webp
`output_quality`	integer	Output quality (for jpg and webp)	`80`	min: 1, max: 100
`seed`	integer	Seed	`-1`	—
`speed_mode`	string	Speed optimization level	`"Extra Juiced 🔥 (more speed)"`	Lightly Juiced 🍊 (more consistent) Juiced 🔥 (default) Extra Juiced 🔥 (more speed) Blink of an eye 👁️ Real Time

img_cond_path required string

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

prompt required string

Prompt

aspect_ratio string

Aspect ratio of the output image

Default: "match_input_image"

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

guidance number

Guidance scale

Default: 3.5

image_size integer

Base image size (longest side)

Default: 1024

num_inference_steps integer

Number of inference steps

Default: 30

output_format string

Output format

Default: "jpg"

png jpg webp

output_quality integer

Output quality (for jpg and webp)

Default: 80 min: 1, max: 100

seed integer

Seed

Default: -1

speed_mode string

Speed optimization level

Default: "Extra Juiced 🔥 (more speed)"

Lightly Juiced 🍊 (more consistent) Juiced 🔥 (default) Extra Juiced 🔥 (more speed) Blink of an eye 👁️ Real Time

Version: 6efb57153457 Updated: 2/26/2026 19.3M runs