Do you remember when I explained what a Large Multimodal Model (LMM) is, and why an LMM is crucial to correctly render text in generative AI-created images?
Well, Black Forest Labs (with an Impressum…in Delaware) announced a new LMM last Thursday:
“FLUX.1 Kontext marks a significant expansion of classic text-to-image models by unifying instant text-based image editing and text-to-image generation. As a multimodal flow model, it combines state-of-the-art character consistency, context understanding and local editing capabilities with strong text-to-image synthesis.”
FLUX.1 Kontext has also received TechCrunch coverage.
And yes, the company does have a German presence.
(And no, the picture is obviously not from FLUX.1 Kontext. It’s from Imagen 4.)
Bredemarket 