FLUX.2 Klein: A Compact 4B Open-Source Image Model
The new 4-billion-parameter model from Black Forest Labs offers an efficient, transformer-based alternative to latent diffusion for image generation.
Black Forest Labs has released FLUX.2 klein, a new 4-billion-parameter open-source model for text-to-image generation and editing. Released under a permissive Apache 2.0 license, the model provides a new, highly efficient option for developers and researchers working with generative AI.
An Alternative to Latent Diffusion
Unlike many popular image models that rely on latent diffusion (the architecture behind Stable Diffusion), FLUX.2 is built on a newer architecture combining flow matching with multimodal transformers. This design aims to achieve high-quality image generation with significantly faster inference speeds, making it a compelling alternative for applications where performance is critical.
The "klein" version is a smaller, more accessible variant of the FLUX.2 architecture. Its relatively compact 4B parameter size makes it easier to run and fine-tune on consumer-grade hardware. As a base model, it's designed to be a strong foundation for a wide range of custom applications, from creative tools to specialized image editors.
The model weights and card for FLUX.2 klein base 4B are available on Hugging Face for immediate use, allowing the community to begin experimenting with this promising new architecture.
Sources
- Visit
black-forest-labs/FLUX.2-klein-base-4B
Hugging Face
More from Black Forest Labs
All Black Forest Labs releases →
Black Forest Labs ships FLUX.3 Image Klein for ComfyUI
The lab's latest open image model arrives packaged for ComfyUI with both generation and editing built in.
Black Forest Labs ships FLUX.3 Image Klein
The latest open image model from the FLUX team handles both text-to-image generation and editing, and arrives ready to run in Diffusers.
Black Forest Labs brings FLUX to robotics
The image-model maker's FLUX 3 Action Base extends its generative stack into world-action modeling, released through the LeRobot ecosystem.
More in Text → Image
All Text → Image →
Bria's Fibo 2.0 Brings Structured Prompts to Open Image AI
The new text-to-image and editing model leans on structured prompts and multi-reference inputs for more controllable generation.
OpenMOSS Releases MOSS-Image Under Apache 2.0
The academic team behind the MOSS project moves into text-to-image generation with a permissively licensed model and a fine-tuned SFT variant.
OpenMOSS Releases Apache-2.0 Bilingual Image Model
MOSS-Image Base arrives as a permissively licensed text-to-image foundation with English and Chinese support.
0 comments
No comments yet. Be the first to weigh in.