black-forest-labs/flux-2-klein-4b-base-lora

A version of FLUX.2 [klein] 4B-base that supports fast fine-tuned lora inference

Capabilities

Seed

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`prompt`*	string	Text prompt for image generation.	`—`	—
`aspect_ratio`	string	Aspect ratio for the generated image. Use 'match_input_image' to match the aspect ratio of the first input image.	`"1:1"`	1:116:99:163:22:34:33:45:44:521:99:21match_input_image
`disable_safety_checker`	boolean	Disable safety checker for generated images.	`false`	—
`images`	array	List of input images for image-to-image generation. Maximum 5 images. Must be jpeg, png, gif, or webp.		—
`lora_scales`	array	Scales for each LoRA as a list of floats. Must match the number of lora_weights. Defaults to 1.0 for each if not provided.	`—`	—
`lora_weights`	array	LoRA weights as a list of URLs. Supports ComfyUI and native Flux Klein format LoRAs. ComfyUI LoRAs are automatically converted.	`—`	—
`output_format`	string	Format of the output images	`"jpg"`	webpjpgpng
`output_megapixels`	string	Resolution of the output image in megapixels	`"1"`	0.250.5124
`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.	`95`	min: 0, max: 100
`seed`	integer	Random seed. Set for reproducible generation	`—`	—

promptrequiredstring

Text prompt for image generation.

aspect_ratiostring

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

Default: "1:1"

1:116:99:163:22:34:33:45:44:521:99:21match_input_image

disable_safety_checkerboolean

Disable safety checker for generated images.

Default: false

imagesarray

List of input images for image-to-image generation. Maximum 5 images. Must be jpeg, png, gif, or webp.

Default:

lora_scalesarray

Scales for each LoRA as a list of floats. Must match the number of lora_weights. Defaults to 1.0 for each if not provided.

lora_weightsarray

LoRA weights as a list of URLs. Supports ComfyUI and native Flux Klein format LoRAs. ComfyUI LoRAs are automatically converted.

output_formatstring

Format of the output images

Default: "jpg"

webpjpgpng

output_megapixelsstring

Resolution of the output image in megapixels

Default: "1"

0.250.5124

output_qualityinteger

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

Default: 95min: 0, max: 100

seedinteger

Random seed. Set for reproducible generation

Version: c8ca755d41ddUpdated: 7/25/20261.3K runs