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 https://civarchive.com/models/299139/splatoon-inkling-xl-locon

I tested it on the fp8 version of Flux, let me know how it works with other quantizations