---
license: other
base_model: "black-forest-labs/FLUX.1-dev"
tags:
  - flux
  - flux-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 tapedeck with a sakura flower design'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'
  output:
    url: ./assets/image_1_0.png
---

# tapedeck-lokr-flux

This is a LyCORIS adapter derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co/black-forest-labs/FLUX.1-dev).


The main validation prompt used during training was:



```
a tapedeck with a sakura flower design
```

## Validation settings
- CFG: `3.0`
- CFG Rescale: `0.0`
- Steps: `20`
- Sampler: `None`
- Seed: `345533`
- Resolution: `800x509`

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: 2300
- Learning rate: 0.0005
- Effective batch size: 2
  - Micro-batch size: 2
  - Gradient accumulation steps: 1
  - Number of GPUs: 1
- Prediction type: flow-matching
- Rescaled betas zero SNR: False
- Optimizer: optimi-lion
- Precision: Pure BF16
- Quantised: Yes: int8-quanto
- Xformers: Not used
- LyCORIS Config:
```json
{
    "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

### tapedeck-512
- Repeats: 5
- Total number of images: 528
- Total number of aspect buckets: 1
- Resolution: 0.262144 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
### tapedeck-1024
- Repeats: 5
- Total number of images: 528
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
### tapedeck-512-crop
- Repeats: 5
- Total number of images: 528
- Total number of aspect buckets: 1
- Resolution: 0.262144 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square
### tapedeck-1024-crop
- Repeats: 5
- Total number of images: 528
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: True
- Crop style: random
- Crop aspect: square


## Inference


```python
import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'black-forest-labs/FLUX.1-dev'
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 tapedeck with a sakura flower design"

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=800,
    height=509,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")
```