metadata

license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
  - sdxl
  - sdxl-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - lora
  - template:sd-lora
  - lycoris
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: >-
      ggn_style, Three women are seated or standing in a grassy area with
      chickens. A fourth woman is seated in front of a thatched-roof hut. Palm
      trees stand nearby. A fifth person appears in the background, engaging
      with the environment. The scene is outdoors and tropical. Text is present
      in the bottom right corner.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png

paul-gaugin-sdxl-lora

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

The main validation prompt used during training was:

ggn_style, Three women are seated or standing in a grassy area with chickens. A fourth woman is seated in front of a thatched-roof hut. Palm trees stand nearby. A fifth person appears in the background, engaging with the environment. The scene is outdoors and tropical. Text is present in the bottom right corner.

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
ggn_style, Three women are seated or standing in a grassy area with chickens. A fourth woman is seated in front of a thatched-roof hut. Palm trees stand nearby. A fifth person appears in the background, engaging with the environment. The scene is outdoors and tropical. Text is present in the bottom right corner.

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: 6
Training steps: 4500
Learning rate: 0.0001
Effective batch size: 8
- Micro-batch size: 8
- Gradient accumulation steps: 1
- Number of GPUs: 1
Prediction type: epsilon
Rescaled betas zero SNR: False
Optimizer: adamw_bf16
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

paul-gaugin-sdxl-512

Repeats: 10
Total number of images: 87
Total number of aspect buckets: 3
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None

paul-gaugin-sdxl-1024

Repeats: 10
Total number of images: 87
Total number of aspect buckets: 17
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None

paul-gaugin-sdxl-512-crop

Repeats: 10
Total number of images: 87
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: random
Crop aspect: square

paul-gaugin-sdxl-1024-crop

Repeats: 10
Total number of images: 87
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 = "ggn_style, Three women are seated or standing in a grassy area with chickens. A fourth woman is seated in front of a thatched-roof hut. Palm trees stand nearby. A fifth person appears in the background, engaging with the environment. The scene is outdoors and tropical. Text is present in the bottom right corner."
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")