Skip to content

black-forest-labs/FLUX.2-klein-4B

Embedl's build black-forest-labs/flux-2-klein-4b of the original model black-forest-labs/FLUX.2-klein-4B

FLUX.2 [klein] 4B
black-forest-labs/flux-2-klein-4b architecture graph
black-forest-labs/flux-2-klein-4b architecture graph
  • huggingface
  • FP8 + BF16 + FP16
  • AGX Thor
Labels
  • Text
  • Image
  • Generation
Build
Embedl-optimized
Precision
FP8 + BF16 + FP16
Runtime
TensorRT 10.16 with Embedl optimizations
Resolution
512×512, 4 steps

Generated by this build

Ran on AGX Thor, this build

  • seed 42

    --prompt

    A red ceramic teapot and a blue cup on a sunlit wooden table.

    Generated image
    Generated image

    Seed 42 · 512 × 512 · 4 steps

  • seed 314

    --prompt

    A tiny observatory on a mossy hill under a clear starry sky, watercolor illustration.

    Generated image
    Generated image

    Seed 314 · 512 × 512 · 4 steps

  • seed 2718

    --prompt

    A neatly arranged collection of colorful glass marbles on white paper, studio photograph.

    Generated image
    Generated image

    Seed 2718 · 512 × 512 · 4 steps

FLUX.2 [klein] 4B is Black Forest Labs' text-to-image model: it generates a 512×512 image from a text prompt in four distilled steps.

Checkpoint e7b7dc27f91deacad38e78976d1f2b499d76a294 (Apache-2.0); Qwen3-4B and the VAE are Apache-2.0.

Files

Image Size

Model

docker.io/embedl/models:hf.black-forest-labs.flux-2-klein-4b.fp8-embedl.thor.2026101817525bbe

—

Runtime

docker.io/embedl/models:flux2-klein.runtime.arm64.2026101814283371

—