Boogu-Image

Yeah, unfortunately, a lot of them have been moving to their own bespoke, non-commercial licenses (Ideogram, Krea, Flux, Qwen 2, etc). Annoyingly, the original Qwen-Image was actually Apache 2 before they switched over unfortunately. In addition to Moss, Boogu Image 0.1 is a unified model which came out in June and is kind of being slept on right now, is actually pretty decent and falls under the Apache 2.0 license. It scored surprisingly high on my GenAI benchmark (comparable to Krea 2 and Ideogram 4). https://github.com/boogu-project/Boogu-Image

Boogu-Image has the Apache 2.0 License [1] (good coherence, but outputs can look synthetic). And Krea 2 has a community license [2] that is fairly permissive - I think commercial usage is allowed under $1 million. Boogu-Image scored 6/15 and Krea 2 scored 7/15 on my GenAI Showdown benchmark [3] - only Ideogram4 eclipses them in terms of local models, but its got a far more restrictive license and the JSON structured inputs can be a pain to work with. [1] - https://github.com/Boogu-Project/Boogu-Image [2] - https://www.krea.ai/krea-2-licensing [3] - https://genai-showdown.specr.net/?models=fd,hd,kd,qi,f2d,zt,...

For locally hostable image editing models, the edit variant of the recently released Boogu-Image[1] model is very good. Anecdotally, I'd say way better than Flux.2 Klein 9B and Qwen-Edit. [1]: https://github.com/boogu-project/Boogu-Image