My first attempt on training a Flux.1 Lora myself on my AMD GPU (RX 7900XT) I uses the same dataset as my previous Inkling Lycoris made for Pony, wich can be found here <a target="_blank" rel="ugc" href="https://civarchive.com/models/299139/splatoon-inkling-xl-locon">https://civarchive.com/models/299139/splatoon-inkling-xl-locon</a> I tested it on the fp8 version of Flux, let me know how it works with other quantizations

Files with SHA256: 44d81a638e8899be7e754e2e740970ecfad29f93217d2372ffaed1ed97f7a8a1