# flux-lora-littletinies

This is a LoRA derived from [FLUX.1-dev/](https://huggingface.co//workspace/SimpleTuner/FLUX.1-dev/).



The main validation prompt used during training was:

```
ethnographic photography of teddy bear at a picnic
```

## Validation settings
- CFG: `7.5`
- CFG Rescale: `0.7`
- Steps: `50`
- Sampler: `None`
- Seed: `42`
- Resolution: `1024`

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: 23
- Training steps: 1800
- Learning rate: 0.0001
- Effective batch size: 16
  - Micro-batch size: 8
  - Gradient accumulation steps: 2
  - Number of GPUs: 1
- Prediction type: epsilon
- Rescaled betas zero SNR: False
- Optimizer: AdamW, stochastic bf16
- Precision: Pure BF16
- Xformers: Enabled
- LoRA Rank: 64
- LoRA Alpha: 16
- LoRA Dropout: 0.1
- LoRA initialisation style: default


## Datasets

### little-tinies
- Repeats: 18
- Total number of images: 64
- Total number of aspect buckets: 1
- Resolution: 1.0 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None


## Inference


```python
import torch
from diffusers import DiffusionPipeline

model_id = '/pzc163/flux-lora-littletinies'
adapter_id = 'flux-lora-littletinies'
pipeline = DiffusionPipeline.from_pretrained(model_id)\pipeline.load_adapter(adapter_id)

prompt = "ethnographic photography of teddy bear at a picnic"
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='blurry, cropped, ugly',
    num_inference_steps=50,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1152,
    height=768,
    guidance_scale=7.5,
    guidance_rescale=0.7,
).images[0]
image.save("output.png", format="PNG")
```

inference: true
widget:
- text: 'unconditional (blank prompt)'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'
  output:
    url: ./image0.png
- text: 'ethnographic photography of teddy bear at a picnic'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'
  output:
    url: ./image1.png
- text: 'a robot walking on the street,surrounded by a group of girls'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'