README.md

metadata

license: other
base_model: stabilityai/stable-diffusion-3.5-large
tags:
  - sd3
  - sd3-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - safe-for-work
  - 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: >-
      A scene from the animated Studio Ghibli movie Spirited Away, where a man
      with kind eyes and a worn hat sits by a window, lost in thought, as light
      filters gently through sheer curtains.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: >-
      A scene from the animated Studio Ghibli movie Spirited Away, where a woman
      with long, windswept hair reads a book at an outdoor cafe, surrounded by
      blooming flowers and soft afternoon light.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: >-
      A scene from the animated Studio Ghibli movie Spirited Away, where a
      fluffy white cat curls up on a windowsill, basking in the warm sunlight,
      while soft curtains flutter in the breeze.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: >-
      A scene from the animated Studio Ghibli movie Spirited Away, where a
      glowing, antlered spirit wanders through a quiet forest, leaving a trail
      of shimmering footprints among the ferns.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: A photo-realistic image of a cat
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_0.png

sd35-spirited-away-lokr

This is a LyCORIS adapter derived from stabilityai/stable-diffusion-3.5-large.

The main validation prompt used during training was:

A photo-realistic image of a cat

Validation settings

• CFG: 4.0
• 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

A scene from the animated Studio Ghibli movie Spirited Away, where a man with kind eyes and a worn hat sits by a window, lost in thought, as light filters gently through sheer curtains.

Negative Prompt

blurry, cropped, ugly

Prompt

A scene from the animated Studio Ghibli movie Spirited Away, where a woman with long, windswept hair reads a book at an outdoor cafe, surrounded by blooming flowers and soft afternoon light.

Negative Prompt

blurry, cropped, ugly

Prompt

A scene from the animated Studio Ghibli movie Spirited Away, where a fluffy white cat curls up on a windowsill, basking in the warm sunlight, while soft curtains flutter in the breeze.

Negative Prompt

blurry, cropped, ugly

Prompt

A scene from the animated Studio Ghibli movie Spirited Away, where a glowing, antlered spirit wanders through a quiet forest, leaving a trail of shimmering footprints among the ferns.

Negative Prompt

blurry, cropped, ugly

Prompt

A photo-realistic image of a cat

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: 3
• Training steps: 600
• Learning rate: 5e-06
• Max grad norm: 0.01
• Effective batch size: 4
  • Micro-batch size: 4
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: flow-matching
• Rescaled betas zero SNR: False
• Optimizer: optimi-stableadamw
• Precision: Pure BF16
• Quantised: No
• Xformers: Not used
• LyCORIS Config:

{
    "bypass_mode": true,
    "algo": "lokr",
    "multiplier": 1.0,
    "full_matrix": true,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 12,
    "apply_preset": {
        "target_module": [
            "Attention"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 6
            }
        }
    }
}

Datasets

screencaps-1024

• Repeats: 0
• Total number of images: 379
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

screencaps-1024-crop

• Repeats: 0
• Total number of images: 379
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square
• Used for regularisation data: No

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'stabilityai/stable-diffusion-3.5-large'
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 = "A photo-realistic image of a cat"
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=4.0,
).images[0]
image.save("output.png", format="PNG")