---
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 a violin serenades the night on a bridge while paper lanterns float in the river below.'
  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 small child with a red scarf wanders through a bustling market filled with strange and colorful creatures.'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'
  output:
    url: ./assets/image_2_0.png
- text: 'A scene from the animated Studio Ghibli movie Spirited Away, featuring a fluffy white cat napping on a train seat as shadows of passengers glide by.'
  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 hundreds of lanterns rise into the starry sky, each carrying a wish from unseen characters.'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'
  output:
    url: ./assets/image_4_0.png
- text: 'A scene from the animated Studio Ghibli movie Spirited Away, where a spirit with glowing eyes floats between the shelves of an endless library, reading ancient books aloud.'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'
  output:
    url: ./assets/image_5_0.png
- text: 'A photo-realistic image of a cat'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'
  output:
    url: ./assets/image_6_0.png
---

# sd35-spirited-away-lokr

This is a LyCORIS adapter derived from [stabilityai/stable-diffusion-3.5-large](https://huggingface.co/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](#training-settings).

You can find some example images in the following gallery:


<Gallery />

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


## Training settings

- Training epochs: 0
- Training steps: 100
- Learning rate: 1e-05
- 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: adamw_bf16
- Precision: Pure BF16
- Quantised: No
- Xformers: Not used
- LyCORIS Config:
```json
{
    "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


```python
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")
```