dataautogpt3/FluxteusV1

<Gallery />

Model description

merge of over 25 plus loras i have trained myself.

it should have decently diffrent representations than base FLUX-1-DEV.

Found way to handle the Loras onto the base checkpoint without causing a leaking on styles/concepts across each other.

Fluxteus is born!

also note this is rather rushed and sloppy on my part. Expect V2 to have a much bigger diffrence.

shoutout to FAL for sponsering me with compute credits and making this possible!

Trigger words

there are multiable diffrent trigger words for diffrent styles and concepts.

detail, photo, anime, CinScene, dreamwalking,

Use it with the :firecracker: diffusers library

from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("dataautogpt3/FluxteusV1", torch_dtype=torch.bfloat16).to('cuda')
image = pipeline('detail photo of a girl').images[0]

License

Please adhere to the licensing terms as described here.