Back to Nodes
Flux Kontext Dev

Flux Kontext Dev

Official

Fast FLUX Kontext editing with exposed tuning controls.

Nodespell AI
AI / Image / Black Forest Labs

Fast FLUX Kontext editing with exposed tuning controls.

FLUX Kontext Dev is the practical choice when you want to experiment from an image reference and tune the result yourself. Guidance, inference steps, seed, aspect ratio, output quality, and output format give more hands-on control than higher-level image nodes.

Use it for draft edits, style exploration, and controlled tests where iteration speed matters. For the most polished Kontext output with fewer low-level decisions, use FLUX Kontext Pro Max.

Model Examples (3)

Example Index01 / 03
Example 01

Example 1

Editorial wardrobe and background variation.

Open
Source Inputs02
Prompt

Restyle the portrait as a clean editorial head-and-shoulders image with a charcoal suit jacket and cool gray background, keeping the face, gaze, crop, and realistic lighting.

Input Image
Example input
Parameters07
Prompt
Restyle the portrait as a clean editorial head-and-shoulders image with a charcoal suit jacket and cool gray background, keeping the face, gaze, crop, and realistic lighting.
Guidance
2.5
Aspect Ratio
match_input_image
Output Format
webp
Output Quality
80
Num Inference Steps
30
Disable Safety Checker
false
Image EditCharacterWardrobePortrait
Response
output
Inputs (2)

prompt

String

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

Multi InputMin: 0Max: 100

Input Image

String

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

Min: 0Max: 100
Parameters (8)

Seed

Number

Random seed for reproducible generation. Leave blank for random.

Prompt

String

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

Default:

Guidance

Number

Guidance scale for generation

Default: 2.5

aspect_ratio

String

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

Default: match_input_image

output_format

String

Output image format

Default: webp

output_quality

Number

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

num_inference_steps

Number

Number of inference steps

Default: 30

disable_safety_checker

Boolean

Disable NSFW safety checker

Default: false
Outputs (1)

response

Inferred

response

Nodespell Team

Creator profile

Type

Node

Status

Official

Package

Nodespell AI

Category

AI / Image / Black Forest Labs

Input

ImageText

Output

Image

Keywords

Image EditStyle TransferAspect ControlResolution Control
Use in Workflow