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 male character in his mid-30s, dressed in a sleek
and agile Assassin's Creed-inspired outfit. He should be standing in a
dramatic pose, with his feet shoulder-width apart and his weight evenly
distributed between both legs. **Clothing:** * The character should wear
a white hooded cloak with a subtle eagle emblem on the shoulder, similar
to Ezio's attire from Assassin's Creed II. * His outfit should consist of
a combination of leather, fabric, and metal armor pieces, with a
predominantly dark grey and white color scheme. * He should have a utility
belt around his waist, complete with pouches, daggers, and other assassin
tools. **Accessories:** * The character should hold a pair of curved
blades, similar to Altaïr's signature weapons, in each hand. * He should
wear a leather glove on his left hand, with a hidden blade mechanism. * A
silver-colored Assassin's Creed emblem should adorn his chest, either as a
brooch or a pendant. **Environment:** * The character should be standing
on a rooftop or a ledge, overlooking a sprawling cityscape at dusk or
dawn. * The background should feature a mix of medieval and
Renaissance-era architecture, with buildings, towers, and churches. * The
atmosphere should be moody and atmospheric, with a warm orange glow from
the setting sun or rising moon. **Lighting:** * The lighting should be
dramatic, with strong shadows cast across the character's face and body. *
A warm, golden light should illuminate the character's features,
highlighting his determined expression. **Expression:** * The
character's face should convey a sense of focus, determination, and
intensity. * His eyes should be narrowed, with a hint of a squint, as if
he's scanning the horizon for potential threats. **Style:** * The image
should be rendered in a highly detailed, realistic style, with textures,
wrinkles, and other subtle details. * The overall aesthetic should evoke a
sense of gritty realism, while still maintaining a sense of fantasy and
adventure.
output:
url: images/example_abvc6bbvt.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