The LoRA was trained on Flux-Dev.It might not work with other Flux Versions. If it works, expect it to behave differently then with Flux-Dev.The showcase images are made with Flux-Dev.This LoRA is intended to be used with text For Flux Dev I recommend the following setting - Lora strength 0.6-1.0, highres fix with denoising 0.3-0.45