About FLUX.2 [klein]
FLUX.2 [Klein] is the fastest model in the Flux family, unifying text-to-image and image editing in one compact architecture. It’s designed for interactive workflows, immediate previews, and latency-critical applications, with distilled variants delivering end-to-end inference around one second while keeping strong quality for single- and multi-reference editing. Model highlights:- Two 4B types: Base (undistilled) for maximum flexibility and fine-tuning; Distilled (4-step) for speed-first deployments
- Performance: distilled ~1.2s (5090) · 8.4GB VRAM; base ~17s (5090) · 9.2GB VRAM
- Editing support: style transforms, semantic edits, object replacement/removal, multi-reference composition, iterative edits
Flux.2 Klein 4B Workflows
4B Text-to-Image Workflow
Download the text-to-image workflow for Flux.2 Klein 4B.
4B Image Edit Base
Download the image editing workflow using the 4B base model.
4B Image Edit Distilled
Download the fast distilled 4B image editing workflow.
Flux.2 Klein 4B Model Downloads
qwen_3_4b.safetensors
Text encoder for 4B models.
flux-2-klein-base-4b-fp8.safetensors
Diffusion model (4B base).
flux-2-klein-4b-fp8.safetensors
Diffusion model (4B distilled).
flux2-vae.safetensors
VAE for 4B models.
Flux.2 Klein 9B Workflows
9B Text-to-Image Workflow
Download the text-to-image workflow for Flux.2 Klein 9B.
9B Image Edit Base
Download the image editing workflow using the 9B base model.
9B Image Edit Distilled
Download the fast distilled 9B image editing workflow.
Flux.2 Klein 9B Model Downloads
For diffusion models, please visit BFL’s repo, accept the agreement, and then download the models.
flux-2-klein-base-9b-fp8.safetensors
Diffusion model (9B base).
flux-2-klein-9b-fp8.safetensors
Diffusion model (9B distilled).
qwen_3_8b_fp8mixed.safetensors
Text encoder for 9B models.
flux2-vae.safetensors
VAE for 9B models.