Please Donate Buzz for FLUX Lora Training !
FLUX v1.0 (Late 1990s) :
Trained on FLUX dev with 40 photos of Actress Ashley Judd in the late 1990s with detailed captions (GPT-4o). Tested on FLUX 1.D (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.9-1.2. No keywords needed! Distilled CFG around 1-4 and CFG 1.0 (without negative prompt). Clipskip 1. Can be used for example as follows:
Positive : {Artstyle, Character and scene description in usual FLUX fashion},<lora:ashelyjudd_local_40_img_merger_19_35_42_03_04_03:1.05>
Description
Please Donate Buzz for FLUX Lora Training !
FLUX v1.0 (Late 1990s) :
Trained on FLUX dev with 40 photos of Actress Ashley Judd in the late 1990s with detailed captions (GPT-4o). Tested on FLUX 1.D (full) and FLUX fp8 and FLUX nf4 ! Use around strength 0.9-1.2. No keywords needed! Distilled CFG around 1-4 and CFG 1.0 (without negative prompt). Clipskip 1. Can be used for example as follows:
Positive : {Artstyle, Character and scene description in usual FLUX fashion},<lora:ashelyjudd_local_40_img_merger_19_35_42_03_04_03:1.05>
FAQ
Comments (9)
I need u version of belle delphine for a sdxl😅
SDXL is much harder to make good loras for. Try going to flux.
@steffangund no problem, I'm waiting for your version of flux for belledelphine, thank you very much
@Ezyn05Â Others have already made Belle Delphine try some of them out!
@steffangund I already tried it, but the results were not good, I hope that one day you can make a lora, have a good day.
@Ezyn05Â Will keep in mind thanks for teh vote of confidence
@steffangund Damn shame that, you made the best SDXL loras for celebs
What happened to the GPT-4 captioned datasets you posted? Did they get deleted? They were really helpful for understanding how to make LoRAS
They were deleted by Civitai