MLLW / README.md
BKKSPY's picture
Add generated example
ea9a4e6 verified
|
raw
history blame
2.71 kB
metadata
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
  - en
tags:
  - flux
  - diffusers
  - lora
  - replicate
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: MLLW
widget:
  - text: >-
      Generate an image of Van Helsing, the legendary vampire hunter, dressed in
      a rugged and worn leather outfit. He should be wearing a long, dark brown
      leather duster coat with multiple pockets and a wide lapel, paired with
      matching leather pants and gloves. His feet should be clad in knee-high,
      lace-up leather boots with a low heel and a subtle brogue pattern.  On his
      head, Van Helsing should wear a wide-brimmed, black leather hat with a
      subtle curve to the brim and a silver band around the crown. The hat
      should be adorned with a few subtle, intricate engravings that hint at his
      supernatural-hunting profession.  In his right hand, Van Helsing should
      hold a ornate, steam-punk inspired gun with intricate engravings and a
      large, flared muzzle. The gun should have a worn, well-used look to it,
      with a few scratches and scuffs on the metal.  Slung over his left
      shoulder, Van Helsing should carry an ornate, hand-carved crossbow with a
      rich, dark wood stock and a intricately designed trigger mechanism. The
      crossbow should be adorned with small, gleaming silver accents and a few
      subtle, mystical symbols etched into the wood.  The overall aesthetic
      should be dark, gritty, and Victorian-inspired, with a hint of steampunk
      flair. The image should evoke a sense of danger, adventure, and
      supernatural mystery. The lighting should be dramatic, with deep shadows
      and a few highlights that accentuate Van Helsing's rugged features and his
      deadly, high-tech weaponry.
    output:
      url: images/example_u5wpbmwvq.png

Mllw

Trained on Replicate using:

https://replicate.com/ostris/flux-dev-lora-trainer/train

Trigger words

You should use MLLW to trigger the image generation.

Use it with the 🧨 diffusers library

from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('BKKSPY/MLLW', weight_name='lora.safetensors')
image = pipeline('your prompt').images[0]

For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers