This lora was trained on official game art and resembles the style really well, IMO. Look at my images for more sample prompts. You can get this style to work with many different types of images. Use it at 1.0 weight and I like to end the prompts like this... in the style of fftstyle
If you have a suggestion for a lora or need a lora trained, feel free to reach out to me.
I use SwarmUI for 95% of my image generations and encourage you to try it out! Here's the link to the OFFICAL GitHub repo and also checkout this install video from Kleebz Tech AI to get you started!
Trigger words
You should use fftstyle to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
from diffusers import AutoPipelineForText2Image
import torch
device = "cuda"if torch.cuda.is_available() else"cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('SouthbayJay/final-fantasy-tactics-style-flux', weight_name='fftstyle_flux_v1.safetensors')
image = pipeline('tshirt design, chevy impala hot rod, city skyline in the background, in the style of fftstyle').images[0]