FLUX 3 Image Klein
FLUX 3 Image Klein is the distilled 5.6B image transformer used behind the Klein API. It supports image editing, text-to-image generation and compositions with up to ten reference images.
Model details
The size label excludes the text encoder. The card requires full-scene caption expansion through a prompt upsampler. Bounding boxes guide layout and scale but are not hard pixel masks. The downloadable package includes image and text components; it needs a compatible inference application.FLUX 3 Image Klein official documentation
Practical use
Practical guidance. Include the text encoder, image decoder and prompt upsampler when estimating local memory. Inspect the expanded prompt when an edit adds unwanted details. Compare the local pipeline with the hosted service, which can apply additional processing around the image model.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | API, Downloadable, Provider product |
| Model identifiers | black-forest-labs/flux-3-image-klein |
| Weight license | FLUX Kommunity License 1.0; commercial-output exception for qualifying users below US$5M gross annualized revenue, including affiliates.FLUX 3 Image Klein official documentation |
| Text encoder | Separate Qwen3-VL-4B-Instruct component, under Apache 2.0.FLUX 3 Image Klein official documentation |
| Sampling recipe | 16 steps without classifier-free guidance.FLUX 3 Image Klein official documentation |
Related models
Undistilled 5.6-billion-parameter image model for generation, editing, fine-tuning and LoRA training.
Launch date not confirmedDownloadableNine-billion-parameter Qwen3.5-based vision-language model that expands image requests into detailed captions.
Launch date not confirmedDownloadable