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 a wealthy man standing in front of a traditional Thai
house in a rural village. The man should be dressed in formal attire,
including: * A crisp, white, long-sleeved dress shirt with a wingtip
collar and French cuffs * Dark brown or black formal trousers with a sharp
crease * Polished, knee-high leather boots with a subtle brogue pattern *
A simple, elegant watch on his wrist The man should be standing
confidently in front of the traditional Thai house, with one hand resting
on the ornate wooden doorframe and the other hand holding a pair of
leather gloves. He should have a relaxed, yet proud expression on his
face. The traditional Thai house should be a large, ornate structure with
multiple tiers and a steeply pitched roof. The exterior walls should be
made of dark wood, with intricate carvings and ornate decorations. The
house should be surrounded by lush greenery, with tropical plants and
trees visible in the background. The image should have a warm, sunny
tone, with a slight sense of nostalgia and elegance. The atmosphere should
evoke a sense of prosperity and refinement, as if the man is a wealthy
landowner or aristocrat who has just returned to his ancestral home.
output:
url: images/example_m3dbqoqfq.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