FLUX 3 Image Klein
Black Forest Labs' 5.6B open image model that generates and edits images from up to 10 references; its INT8 build fits in 8 GB of VRAM.
In short. FLUX 3 Image Klein is a compact image model you can run on your own graphics card. You can describe a picture in words, edit an existing photo with an instruction, combine up to ten reference images, or draw boxes to say where things should go. It is free for personal use and for small businesses under US$5 million a year in revenue.
Summary
Black Forest Labs released FLUX 3 Image Klein on 15 October 2026. It is a 5.6-billion-parameter diffusion model, a size count that covers the image transformer only; the Qwen3-VL-4B-Instruct text encoder is separate. A single model handles text-to-image, instruction-based editing, composition from up to 10 reference images, and layout control: you place bounding boxes on a 0 to 1000 grid in the prompt and then move, recolor, replace or remove the elements inside them. It renders text inside images and outputs up to 4K.
Two checkpoints are open. The distilled Klein runs in 16 steps without classifier-free guidance and is the one to self-host; the undistilled Klein Base takes 50 steps and is meant for fine-tuning, LoRA training and research. The BF16 generator weights are about 11 GB and the FP8 ones about 5.6 GB, and an INT8 build runs on NVIDIA GPUs with as little as 8 GB of VRAM through ComfyUI or Diffusers. NVFP4 builds need a Blackwell GPU. The pipeline also needs a separate Qwen3-VL-4B text encoder, about 9 GB in BF16. Hugging Face's Diffusers team measured a peak of 20.7 GiB (about 22 GB) with BF16 weights and no CPU offloading, and Black Forest Labs says a 1-megapixel image takes about 4 seconds on an RTX 5090 and under 9 seconds on an RTX 4070.
You should always run its prompt upsampler. The model was trained on long, detailed scene captions, and a short prompt sent as typed gives generic results. Black Forest Labs provides one: a 9B vision-language model fine-tuned from Qwen3.5-9B and released under Apache 2.0. The reference code, Diffusers and the ComfyUI workflows enable it by default.
The weights use the FLUX Kommunity License: free for non-commercial use, and free for commercial use only if you and your affiliates have annual revenue under US$5 million. Larger organizations need a separate commercial license or the paid API. The download is gated on Hugging Face; you accept the license and are approved automatically. In Black Forest Labs' own internal evaluations the model ranks first among open image models for text-to-image, multi-reference generation and editing; those results are the developer's and have not been independently confirmed. Day-one support covers ComfyUI, Diffusers, SGLang Diffusion and vLLM-Omni.
Good for
- Editing photos from an instruction, or merging several reference images into one
- Layout-controlled generation, where you decide where each element goes with boxes
- Local image generation on a consumer GPU, down to 8 GB of VRAM with the INT8 build
- Hobbyists and companies under US$5 million in revenue who want commercial use without paying
- Fine-tuning and LoRA training on the Klein Base checkpoint
Watch out for
- Not Apache 2.0: companies above US$5 million in annual revenue need a separate commercial license
- Commercial users must filter or review outputs and add AI disclosures where required, and may not use outputs to train competing models
- Always use the prompt upsampler; short prompts give noticeably weaker images
- The weights are gated on Hugging Face and need an account and license acceptance
- The 8 GB figure applies to the INT8 build and the text encoder is extra weight; NVFP4 needs a Blackwell GPU
- If you want a fully permissive license, BFL's earlier FLUX.2 klein 4B is listed on Hugging Face under Apache 2.0
Performance claims come from the developer and have not been independently verified.
How much memory does it need?
Memory figures for each variant of FLUX 3 Image Klein. Image, video, speech and music pipelines also load a text encoder and a decoder, so the memory needed can be larger than the main checkpoint.
| Variants | Parameters | Download size | Memory needed | Fits on |
|---|---|---|---|---|
| Klein (distilled, 16 steps) BF16 | 5.6B | 20 GB | 22 GB | Gaming GPU |
| Klein Base (50 steps, for fine-tuning) BF16 | 5.6B | 20 GB | 22 GB | Gaming GPU |
| Klein INT8 (ComfyUI) INT8 | 5.6B | 11 GB | 8 GB | Laptop or phone |
Download size covers every component needed to run the model, such as the generator, text encoder and decoder. Memory needed is a stated or published measured minimum where one exists; otherwise it is the download size plus about 15%. Larger images, longer clips and higher resolutions need more. The developer states a minimum of 8 GB of GPU memory.
The license in plain words
Black Forest Labs' license for its open FLUX 3 weights. It is free for personal and non-commercial use, and free for commercial use only by "Qualifying Users", meaning you and your affiliates earn under US$5 million a year. Larger companies need a commercial license or the paid API.
- Free commercial use only below a revenue cap
- Outputs must be filtered or reviewed, and AI generation disclosed
- Acceptable-use policy applies
See also
- FLUX 3 Klein vs Krea 2: which image model to pick?
- FLUX 3 Image Klein vs Qwen-Image-2.1: licenses, memory and features
- FLUX.3 Image Klein vs Z-Image: which open image model should you use?
- Best open-source image and video generation models
- Open-weight AI models made in Europe
- Free until you grow: where open licenses draw the line
- Krea 2: an open image model trained from scratch for variety
- MiniMax H3-Image: 16-megapixel open weights, but not for the US or EU
- MOSS-Image: a 5B open image model for long text and JSON layouts
- Black Forest Labs releases FLUX 3 Image Klein with layout control
Frequently asked questions
- What is FLUX 3 Image Klein?
- FLUX 3 Image Klein is a compact image model you can run on your own graphics card. You can describe a picture in words, edit an existing photo with an instruction, combine up to ten reference images, or draw boxes to say where things should go. It is free for personal use and for small businesses under US$5 million a year in revenue.
- Can I use FLUX 3 Image Klein commercially?
- Yes, with conditions. FLUX 3 Image Klein is released under the FLUX Kommunity, which allows commercial use but adds extra rules: Free commercial use only below a revenue cap; Outputs must be filtered or reviewed, and AI generation disclosed; Acceptable-use policy applies. Read the license text before you ship a product.
- Is FLUX 3 Image Klein open source?
- FLUX 3 Image Klein is open-weight, not open source in the strict sense. You can download the model files, but the FLUX Kommunity adds conditions that the Open Source Initiative definition does not allow.
- Can I run FLUX 3 Image Klein on my own computer?
- Yes. The smallest variant, Klein INT8 (ComfyUI), needs about 8 GB of memory at 4-bit precision, which fits a modern laptop or a mid-range graphics card.
- When was FLUX 3 Image Klein released?
- FLUX 3 Image Klein was released by Black Forest Labs on October 15, 2026.
Official links
Sources
Specifications come from these primary sources. Benchmark claims, where mentioned, are reported by the developer.
- Black Forest Labs: FLUX 3 Image Klein, open weights, 5.6B parameters (15 Oct 2026) bfl.ai
- FLUX 3 Image Klein model card (Hugging Face) huggingface.co
- Reference inference code (GitHub) github.com
- BFL release notes docs.bfl.ml
- Hugging Face blog: FLUX.3 Image Klein in Diffusers (memory measurements) huggingface.co
Release date and facts last verified November 8, 2026.
Related models
| Model | Released | Parameters | Context | License | Smallest variant needs |
|---|---|---|---|---|---|
| Qwen-Image-2.1 Alibaba Qwen | 7.1B | – | Qwen Research License (Non-commercial) | 20 GB Gaming GPU | |
| LTX-2.5 LTX (Lightricks) | 22B | – | LTX-2.x Community (Conditional) | 16 GB Laptop or phone | |
| Z-Image Tongyi MAI | 6.15B | – | Apache 2.0 (Permissive) | 16 GB Laptop or phone | |
| MiniMax H3-Image MiniMax | 33.1B | – | MiniMax H3-Image Community (Conditional) | 155 GB Big-memory desktop |