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 humble scene in rural Thailand. In the center of
the image, depict a man standing in front of a small, traditional Thai
house with a thatched roof. The house should be simple, with wooden walls
and a corrugated metal door. The thatched roof should be worn and slightly
disheveled, with some straw or leaves sticking out. The MLLW with thin and
lean ,long hair, The MLLW should be dressed in worn, earth-toned clothing,
consisting of a loose-fitting farmer's shirt with buttons undone,
revealing a plain white undershirt. His pants should be faded and patched
in places, with a wide belt holding them up. He should wear scuffed and
dusty boots that look like they've seen many years of hard work. The man's
facial expression should be kind and weary, with deep lines etched on his
face from years of working under the sun. He should have a gentle gaze,
looking directly at the viewer with a sense of quiet dignity.
output:
url: images/example_it716hbz4.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