đ lora-Kirchner-flux
This is a LoRA model derived from black-forest-labs/FLUX.1-dev, which can generate text-to-image results based on the pre - trained model.
đ Quick Start
Validation Prompt
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
Property |
Details |
CFG |
7.5 |
CFG Rescale |
0.0 |
Steps |
20 |
Sampler |
None |
Seed |
42 |
Resolution |
1024 |
â ī¸ Important Note
The validation settings are not necessarily the same as the training settings.
Example Images
You can find some example images in the following gallery:
Text Encoder
The text encoder was not trained. You may reuse the base model text encoder for inference.
⨠Features
This LoRA model has the following features:
- Based on the
black-forest-labs/FLUX.1-dev
base model.
- Can generate images according to specific prompts.
- Provide clear validation and training settings.
đĻ Installation
There is no specific installation command provided in the original document, so this section is skipped.
đģ Usage Examples
Basic Usage
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")
đ Documentation
Training Settings
Property |
Details |
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
Property |
Details |
Repeats |
0 |
Total number of images |
102 |
Total number of aspect buckets |
1 |
Resolution |
1024 px |
Cropped |
True |
Crop style |
center |
Crop aspect |
square |
đ§ Technical Details
The model is based on the LoRA technique, which is a parameter - efficient fine - tuning method. By adjusting the LoRA rank, alpha, dropout and other parameters, the model can adapt to specific datasets and tasks. The training process uses specific optimizers and precision settings to improve training efficiency and performance.
đ License
The license of this project is creativeml-openrail-m
.