par ostris
Open source · 149k downloads · 679 likes
OpenFLUX.1 est un modèle d'IA spécialisé dans la génération d'images à partir de texte, offrant une alternative open source et personnalisable au modèle FLUX.1-schnell. Contrairement à sa version originale, il a été affiné pour supprimer les contraintes de distillation, permettant ainsi des ajustements et des optimisations plus poussés. Ce modèle se distingue par sa capacité à produire des images de haute qualité tout en restant accessible pour des usages variés, allant de la création artistique à l'illustration professionnelle. Son approche classique de la configuration (CFG) le rend particulièrement adapté aux utilisateurs souhaitant explorer des techniques avancées de génération. Enfin, sa licence permissive en fait un outil idéal pour les développeurs et chercheurs souhaitant l'adapter à leurs besoins spécifiques.
After numerous iterations and spending way too much of my own money on compute to train this, I think it is finally at the point I am happy to consider it a beta. I am still going to continue to train it, but the distillation has been mostly trained out of it at this point. So phase 1 is complete. Feel free to use it and fine tune it, but be aware that I will likely continue to update it.
This is a fine tune of the FLUX.1-schnell model that has had the distillation trained out of it. Flux Schnell is licensed Apache 2.0, but it is a distilled model, meaning you cannot fine-tune it. However, it is an amazing model that can generate amazing images in 1-4 steps. This is an attempt to remove the distillation to create an open source, permissivle licensed model that can be fine tuned.
Since the distillation has been fine tuned out of the model, it uses classic CFG. Since it requires CFG, it will require a different pipeline than the original FLUX.1 schnell and dev models. This pipeline can be found in open_flux_pipeline.py in this repo. I will be adding example code in the next few days, but for now, a cfg of 3.5 seems to work well.
