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
base_model: black-forest-labs/FLUX.1-dev
pipeline_tag: text-to-image
instance_prompt: AQUACOLTOK
widget:
- text: >-
A painting of a mountain climber reaching the summit of a peak, with the
word 'ASCEND' appearing in the snow patterns on the mountain's surface. In
a watercolor style, AQUACOLTOK. White background.
output:
url: images/ascend.webp
- text: >-
A painting of a vintage-style travel poster, with a suitcase and globe in
the foreground, and the words "Destination Unknown" printed in a
beautiful, cursive font on a distressed luggage tag. In a watercolor
style, AQUACOLTOK. White background.
output:
url: images/vintage.webp
- text: >-
A painting of a quaint, old-fashioned bookstore, with the words "Tales of
Wonder" etched in gold lettering above the storefront. In a watercolor
style, AQUACOLTOK. White background.
output:
url: images/bookstore.webp
- text: >-
A painting of a person giving a TED talk on a TED stage with the TED logo,
"the speaker". In a watercolor style, AQUACOLTOK.
output:
url: images/ted.webp
- text: >-
A painting of a barista creating an intricate latte art design, with the
"Coffee Creations" logo skillfully formed within the latte foam. In a
watercolor style, AQUACOLTOK. White background.
output:
url: images/coffee.webp
Works best with the template:
A painting of ... In a watercolor style, AQUACOLTOK. White background.
Flux_Lora_Aquarel_Watercolor
Trained on Replicate using:
https://replicate.com/ostris/flux-dev-lora-trainer/train
Trigger words
You should use AQUACOLTOK
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('SebastianBodza/flux_lora_aquarel_watercolor', 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