5.6B-parameter open-weights model from Black Forest Labs for image editing, text-to-image and multi-reference composition.
Updated EU status checked Last shown
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
FLUX 3 Image Klein is a 5.6B-parameter image model from Black Forest Labs. A single set of weights handles instruction-based image editing, text-to-image generation, and composition from up to ten reference images. It also supports layout control with bounding boxes, where each element gets a box and a description on a 0–1000 grid.
BFL releases an undistilled version for fine-tuning and research and a distilled version for fast editing and generation. The model is designed to run on a single consumer GPU. Output up to 4K is available through the BFL API. It is meant to be used with a prompt upsampler, which is included automatically in the API and available separately for self-hosted use.
Weights and the prompt upsampler are downloaded from Hugging Face and can be run in ComfyUI or a custom pipeline. They are released under the license on the Hugging Face model card. BFL states that running Klein in a product requires a commercial license for self-hosted deployment at scale. One YouTube reviewer described the license as non-commercial community and reported weak faces and anatomy in his tests.
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Small 5.6B open image generation/editing model with 4K support and bounding box control, available in ComfyUI under a non-commercial community license. The creator's tests showed bad faces and anatomy, so he passes on it.
Open-weight image model with weights on Hugging Face. It runs on consumer GPUs like an RTX 4070 and on a DGX Spark, and can be tried free on Spaces. The creator found it decent but not special apart from being open.
Closest neighbours by meaning, not just by category.
Model · Black Forest Labs
9B-parameter open-weights image generation and editing model from Black Forest Labs, built for low-latency use.
Model · Black Forest Labs
Black Forest Labs image model with bounding-box layout control, reference-image input and native 4K output.
Model · Black Forest Labs
7B open-weights world action model from Black Forest Labs that jointly predicts video and actions for robot control.
Model · Black Forest Labs
Black Forest Labs' video generation model in the FLUX 3 family, with native audio and clips up to 20 seconds.
Model
Open-weights 6B text-to-image model family from Alibaba's Tongyi-MAI lab, with a fast 8-step Turbo variant.
Model · OpenMOSS
Open-weights 5B text-to-image model family from OpenMOSS with native JSON bounding-box layout control and text rendering.
