eugene-boudin-sdxl-01

This is a LyCORIS adapter derived from stabilityai/stable-diffusion-xl-base-1.0.

The main validation prompt used during training was:

bdn_style, A harbor at sunset. Multiple ships with masts and sails are anchored. Small rowboat with two people in the water. Pier extends from left. Land with trees and buildings in the background. Text at bottom left.

Validation settings

• CFG: 4.2
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• Seed: 42
• Resolution: 1024x1024

Note: The validation settings are not necessarily the same as the training settings.

You can find some example images in the following gallery:

Prompt

unconditional (blank prompt)

Negative Prompt

blurry, cropped, ugly

Prompt

bdn_style, painting of a hipster making a chair

Negative Prompt

blurry, cropped, ugly

Prompt

bdn_style, painting of a hamster

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of bdn_style, A bustling coastal market scene under a dramatic, stormy sky. Vendors with colorful umbrellas sell their wares as dark clouds gather overhead. Fishing boats bob in the choppy harbor waters. A lighthouse stands sentinel in the distance, its beam cutting through the approaching tempest.

Negative Prompt

blurry, cropped, ugly

Prompt

bdn_style, A group of elegantly dressed people enjoying a picnic on the beach at sunset. The sky is ablaze with vibrant oranges and purples, reflecting off the calm sea. Parasols and blankets dot the sand, while a steam train puffs along a distant coastal track, leaving a trail of smoke that merges with the clouds.

Negative Prompt

blurry, cropped, ugly

Prompt

bdn_style, an airliner flying over a body of water at sunset

Negative Prompt

blurry, cropped, ugly

Prompt

bdn_style, A harbor at sunset. Multiple ships with masts and sails are anchored. Small rowboat with two people in the water. Pier extends from left. Land with trees and buildings in the background. Text at bottom left.

Negative Prompt

blurry, cropped, ugly

The text encoder was not trained. You may reuse the base model text encoder for inference.

Training settings

• Training epochs: 15
• Training steps: 10000
• Learning rate: 0.0001
• Effective batch size: 4
  • Micro-batch size: 4
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: epsilon
• Rescaled betas zero SNR: False
• Optimizer: optimi-lionweight_decay=1e-3
• Precision: Pure BF16
• Quantised: Yes: int8-quanto
• Xformers: Not used
• LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 16,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

eugene-boudin-sdxl-512

• Repeats: 10
• Total number of images: 53
• Total number of aspect buckets: 4
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

eugene-boudin-sdxl-1024

• Repeats: 10
• Total number of images: 53
• Total number of aspect buckets: 2
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

eugene-boudin-sdxl-512-crop

• Repeats: 10
• Total number of images: 53
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

eugene-boudin-sdxl-1024-crop

• Repeats: 10
• Total number of images: 53
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'stabilityai/stable-diffusion-xl-base-1.0'
adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
wrapper.merge_to()

prompt = "bdn_style, A harbor at sunset. Multiple ships with masts and sails are anchored. Small rowboat with two people in the water. Pier extends from left. Land with trees and buildings in the background. Text at bottom left."
negative_prompt = 'blurry, cropped, ugly'
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    negative_prompt=negative_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=4.2,
    guidance_rescale=0.0,
).images[0]
image.save("output.png", format="PNG")