flux-3-image-klein

Ungated mirror of black-forest-labs/flux-3-image-klein-base, republished by Unsloth so it can be downloaded without a Hub gate. The weights are unmodified. See NOTICE.md and LICENSE.md in this repo for the terms, which are the upstream terms and are unchanged.

FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. It takes a prompt and up to 10 reference images and returns one image. Text-to-image, single-reference edits and multi-reference compositions run through the same model, with Qwen3-VL-4B-Instruct as the text encoder.

The 5.6B parameter label refers to the image transformer; the text encoder is separate.

This repository holds the undistilled base checkpoint, for fine-tuning, LoRA training and research. You can find the distilled checkpoint here: FLUX 3 Image Klein.

Inference code, prompt upsampling and the bounding box format: black-forest-labs/flux-3-image-klein on GitHub.

Do not use the model without a prompt upsampler. FLUX 3 Image Klein takes full scene captions, for text-to-image, editing and layout with boxes alike; a short prompt sent as typed gives generic output. Use ours, flux-3-image-klein-pup, which the reference code loads by default, or any LLM you prefer with a system prompt that expands the request into one full scene caption (system_prompts.json has ours). Diffusers runs neither on its own; see Prompt upsampling.

This repository includes the BF16 transformer and FP8 and NVFP4 variants, together with the Qwen3-VL-4B-Instruct text encoder and image autoencoder.

Key Features

1. Text-to-image, single-reference editing and multi-reference generation in one model.
2. Bounding boxes in the prompt. Place elements with boxes on a 0 to 1000 grid, then recolor, move, replace or remove them through the prompt. Boxes guide placement and scale; they do not constrain pixels to a hard mask.
3. Text rendering within generated images.
4. Released under the FLUX Kommunity License. The license permits non-commercial use and provides a commercial-output exception for Qualifying Users, subject to its terms. See License below.

Download

Download the root BF16 package and shared components without downloading the quantized variants:

from huggingface_hub import snapshot_download

snapshot_download(
    repo_id="black-forest-labs/flux-3-image-klein-base",
    local_dir="weights/flux-3-image-klein-base",
    allow_patterns=[
        "model.safetensors", "config.json", "manifest.json",
        "ae.safetensors", "text_encoder/*",
        "README.md", "LICENSE.md", "NOTICE.md",
    ],
)

To download a quantized transformer instead, replace the three root transformer patterns (model.safetensors, config.json, and manifest.json) with variants/fp8r/* or variants/nvfp4/*. Keep ae.safetensors and text_encoder/* for the shared components.

These files contain the model package, not a complete inference application. Use an inference implementation that supports this checkpoint format. Quantized packages need a loader that supports their format; their file size is not a measure of total GPU memory use.

Using with reference code

The distilled checkpoint is served on the BFL API as FLUX 3 Image Klein. The reference inference code is black-forest-labs/flux-3-image-klein.

From the reference implementation checkout, install the package and download the two components the CLI loads besides this checkpoint. The CLI reads its weights from weights/ (set WEIGHTS_DIR for another root), where the download above puts this repository.

pip install -e .

# safety classifier, always loaded
hf download Falconsai/nsfw_image_detection --local-dir weights/nsfw-classifier
# prompt upsampler (18.8 GB), on by default; --no-pup sends the prompt as typed, for captions written by another LLM
hf download black-forest-labs/flux-3-image-klein-pup --local-dir weights/pup

# text-to-image
python scripts/cli.py 'A chunky knitted diorama: three white cable-knit icebergs with tiny pale blue houses, a cream banner embroidered "KNITTED ICEBERG VILLAGE", a giant magenta knitted whale tail bursting from a yarn sea' \
  --model base --out knitted.png

# image editing; repeat --image for multiple references
python scripts/cli.py 'the same scene at night under a knitted full moon, embroidered stars above the peaks' \
  --model base --image knitted.png --out knitted_night.png

Using with Diffusers

FLUX 3 Image Klein uses a modular pipeline. Pass prompt for text-to-image generation, or pass image with a prompt for editing; image can be one image or a list of reference images. The model takes full scene captions, not short prompts: a request sent as typed gives generic output. Every request below goes through the prompt upsampler first, a separate 9B model ([black-forest-labs/flux-3-image-klein-pup](https://huggingface.co/blac