What is FLUX.2 [klein]?

FLUX.2 [klein] is a compact and fast Flux.2 series model that can handle both Image Generation and Instruction-based Image Editing with a single model.

Lineup:

  • 9B / 9B Base (FLUX Non-Commercial License)
  • 4B / 4B Base (Apache 2.0)

It's a bit confusing, but the one without "Base" is the Distilled model. While Base requires 20 steps, Distilled can generate in 4 steps.

Since there is no significant difference in performance, we will basically use the Distilled model for generation.

Recommended Settings

  • Resolution
    • Min: 64×64
    • Max: 4MP (2048×2048)
    • Both width and height must be multiples of 16
  • Number of Reference Images
    • Max: 4

Flux.2 [klein] 9B

Model Download (9B)

📂ComfyUI/
└── 📂models/
    ├── 📂diffusion_models/
    │   ├── flux-2-klein-9b-fp8.safetensors
    │   └── flux-2-klein-base-9b-fp8.safetensors
    ├── 📂text_encoders/
    │   └── qwen_3_8b.safetensors
    └── 📂vae/
        └── flux2-vae.safetensors

text2image Base

flux_2_klein_base_9b_text2image.json

The official workflow uses Flux2Scheduler, but since there is no major difference, we use Simple to simplify the workflow.

text2image Distilled

flux_2_klein_9b_text2image.json

Change only the following parameters:

  • CFG : 1.0
  • steps : 4

Image Editing Base

flux_2_klein_base_9b_image_edit.json

"Input Image + Instruction Prompt" is the basic method.

  • VAE Encode the input image and pass it to ReferenceLatent.

Image Editing Distilled

flux_2_klein_9b_image_edit.json

Image Editing (Multi-Reference) Base

You can also input and reference multiple images.

flux_2_klein_base_9b_image_edit_multi.json
  • Just connect the block of Reference Image → VAE Encode → ReferenceLatent in series.
  • 2 or 3 images are OK. (Maximum is 4)

Image Editing (Multi-Reference) Distilled

flux_2_klein_9b_image_edit_multi.json

Flux.2 [klein] 4B

Model Download (4B)

📂ComfyUI/
└── 📂models/
    ├── 📂diffusion_models/
    │   ├── flux-2-klein-4b.safetensors
    │   └── flux-2-klein-base-4b.safetensors
    ├── 📂text_encoders/
    │   └── qwen_3_4b.safetensors
    └── 📂vae/
        └── flux2-vae.safetensors

Workflow

The basics are exactly the same as 9B. Just replace the model and text encoder with the 4B ones.

text2image

  • flux_2_klein_base_4b_text2image.json
  • flux_2_klein_4b_text2image.json

Image Editing

  • flux_2_klein_base_4b_image_edit.json
  • flux_2_klein_4b_image_edit.json

Image Editing (Multi-Reference)

  • flux_2_klein_base_4b_image_edit_multi.json
  • flux_2_klein_4b_image_edit_multi.json

Capabilities / Examples

These are just a few examples.

Changing style or removing objects is only a small part of image editing. The possibilities are endless depending on what you consider "image editing". Please explore various uses.

Single Image

WorkflowsSingle Image
flux_2_klein_9b_style_transfer.json

Style Transfer

Reskin this into a watercolor illustration on textured paper.
flux_2_klein_9b_environmental_change.json

Environmental / State Change

Change the time to bright midday.
flux_2_klein_9b_object_swap.json

Object Swap / Addition

Replace the ice bear with an ice duck. Add a hat on the duck with light blue, red, and white colors. Add sneakers on the duck.
flux_2_klein_9b_text_edit.json

Text Editing

Edit the text "WELCOME" to "Flux.2".
flux_2_klein_9b_restore.json

Image Restoration

Restore and colorize this black-and-white photo.
flux_2_klein_9b_pose.json

ControlNet-like (Pose)

It does not work on the mechanism of ControlNet. By providing a stick figure or depth map and asking it to generate a realistic image based on it, you can perform ControlNet-like tasks as image editing.

A office lady sitting on outdoor stairs at dusk, matching the pose from the reference image. Evening ambient light, calm urban atmosphere. She wears a long skirt and a black camisole with frills. Natural, realistic photo
flux_2_klein_9b_outpainting.json

inpainting / outpainting

It doesn't fill in the masked area, but you just instruct it to "fill the gray area naturally".

Outpaint the gray areas to extend the scene naturally
flux_2_klein_9b_collage_refinement.json

Collage Refinement

Turn this into a single realistic underwater ruins scene with two robots: a sleek white mecha and a large rusty moss-covered robot.

Multi-Reference Image Editing

WorkflowsMulti-Reference Image Editing
flux_2_klein_9b_style_transfer_multi.json

Style Transfer

Change image 1 to match the style of image 2.
flux_2_klein_9b_object_swap_multi.json

Object / Person Swap

Replace the person in image 1 with the person from image 2.
flux_2_klein_9b_object_add_multi.json

Add Object

Place the airship from image 2 in the sky of image 1,Make the airship prominent (closer to camera)

References