metadata
license: creativeml-openrail-m
base_model: black-forest-labs/FLUX.1-dev
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- simpletuner
- lora
- template:sd-lora
inference: true
widget:
- text: unconditional (blank prompt)
parameters:
negative_prompt: blurry, cropped, ugly
output:
url: ./assets/image_0_0.png
- text: >-
elk_style, Whimsical kitchen scene: man with feathered hat, striped
scarf, and exaggerated features stands with arms outstretched, as if
proclaiming; concerned woman in old-fashioned dress and apron sits at
table with frying pan, surrounded by utensils and dishes, against a
backdrop of brick wall, curtained window, and wooden floor with rug.
output:
url: images/example_2wixkomof.png
- text: >-
elk_style, The image is a painting of a busy street scene in Paris,
France. The painting is done in a realistic style with loose brushstrokes
and vibrant colors. It shows a woman walking on the street, wearing a blue
skirt and a black top hat with a red pom-pom on top. She is carrying a
white box in her hand and appears to be looking down at it. On the left
side of the painting, there is a street lamp post with a sign that reads
"Cafe". On the right side, there are several buildings with ornate
architectural details, including a horse-drawn carriage and a group of
people walking on a sidewalk. The sky is overcast and the ground is wet,
suggesting that it has recently rained.
output:
url: images/example_8o7mwv5ph.png
lora-Kirchner-flux
This is a LoRA derived from black-forest-labs/FLUX.1-dev.
The main validation prompt used during training was:
The image is a black and white illustration of a man with a long beard and a long white beard, sitting on the ground with his arms raised above his head. He appears to be in a meditative pose, with his eyes closed and a peaceful expression on his face. Behind him, there are two other men, one lying on their backs and the other lying down. The background shows a mountain landscape with a cloudy sky. The text above the illustration reads 'Let the day perish where I was born. And they sat down with him upon the ground seven days & seven nights and none spoke a word unto him for they saw that his grief was very great.' The illustration is framed by a decorative border.
Validation settings
- CFG:
7.5
- CFG Rescale:
0.0
- Steps:
20
- Sampler:
None
- Seed:
42
- Resolution:
1024
Note: The validation settings are not necessarily the same as the training settings.
You can find some example images in the following gallery:
The text encoder was not trained. You may reuse the base model text encoder for inference.
Training settings
- Training epochs: 235
- Training steps: 4000
- Learning rate: 0.0001
- Effective batch size: 6
- Micro-batch size: 6
- Gradient accumulation steps: 1
- Number of GPUs: 1
- Prediction type: flow-matching
- Rescaled betas zero SNR: False
- Optimizer: AdamW, stochastic bf16
- Precision: Pure BF16
- Xformers: Not used
- LoRA Rank: 64
- LoRA Alpha: None
- LoRA Dropout: 0.1
- LoRA initialisation style: default
Datasets
ErnstLudwigKirchner
- Repeats: 0
- Total number of images: 102
- Total number of aspect buckets: 1
- Resolution: 1024 px
- Cropped: True
- Crop style: center
- Crop aspect: square
Inference
import torch
from diffusers import DiffusionPipeline
model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'davidrd123/lora-Kirchner-flux'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)
prompt = "The image is a black and white illustration of a man with a long beard and a long white beard, sitting on the ground with his arms raised above his head. He appears to be in a meditative pose, with his eyes closed and a peaceful expression on his face. Behind him, there are two other men, one lying on their backs and the other lying down. The background shows a mountain landscape with a cloudy sky. The text above the illustration reads 'Let the day perish where I was born. And they sat down with him upon the ground seven days & seven nights and none spoke a word unto him for they saw that his grief was very great.' The illustration is framed by a decorative border."
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
prompt=prompt,
num_inference_steps=20,
generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
width=1024,
height=1024,
guidance_scale=7.5,
).images[0]
image.save("output.png", format="PNG")