---
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
- standard
inference: true
widget:
- text: >-
    In the style of a b3nbr4nd painting,  Massive green serpent, coiled around a
    cracked stone obelisk, golden eyes glowing, dark blue scales with iridescent
    shimmer, open mouth revealing sharp fangs, pink sky fading into deep purple,
    sand dunes stretching into the horizon, ancient ruins partially buried, red
    banners flapping in the wind.
  output:
    url: images/example_93zee9o4f.png
- text: >-
    In the style of a b3nbr4nd painting, The Fractured Cathedral – Ruined temple
    standing between timelines, stained glass windows refracting multiple
    realities, golden gears turning in the vaulted ceiling, priests in robes of
    shifting colors, a mechanical choir humming in binary, relics of forgotten
    AI scattered on an altar, static crackling like divine whispers.
  output:
    url: images/example_4d6wwz6le.png

---

# Ben-Brand-LoRA

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


No validation prompt was used during training.

None



## Validation settings
- CFG: `3.0`
- CFG Rescale: `0.0`
- Steps: `20`
- Sampler: `FlowMatchEulerDiscreteScheduler`
- Seed: `42`
- Resolution: `1024x1024`
- Skip-layer guidance: 

Note: The validation settings are not necessarily the same as the [training settings](#training-settings).




<Gallery />

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


## Training settings

- Training epochs: 2
- Training steps: 3750
- Learning rate: 0.00015
  - Learning rate schedule: constant
  - Warmup steps: 100
- Max grad norm: 0.1
- Effective batch size: 6
  - Micro-batch size: 2
  - Gradient accumulation steps: 3
  - Number of GPUs: 1
- Gradient checkpointing: True
- Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flow_matching_loss=compatible', 'flux_lora_target=all'])
- Optimizer: adamw_bf16
- Trainable parameter precision: Pure BF16
- Caption dropout probability: 10.0%


- LoRA Rank: 64
- LoRA Alpha: None
- LoRA Dropout: 0.1
- LoRA initialisation style: default
    

## Datasets

### ben-brand-256
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 3
- Resolution: 0.065536 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-256
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 0.065536 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### ben-brand-512
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 3
- Resolution: 0.262144 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-512
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 0.262144 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### ben-brand-768
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 3
- Resolution: 0.589824 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-768
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 0.589824 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### ben-brand-1024
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 4
- Resolution: 1.048576 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-1024
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### ben-brand-1440
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 2
- Resolution: 2.0736 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-1440
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 2.0736 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No


## Inference


```python
import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'davidrd123/Ben-Brand-LoRA'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "An astronaut is riding a horse through the jungles of Thailand."


## Optional: quantise the model to save on vram.
## Note: The model was quantised during training, and so it is recommended to do the same during inference time.
from optimum.quanto import quantize, freeze, qint8
quantize(pipeline.transformer, weights=qint8)
freeze(pipeline.transformer)
    
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
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(42),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")
```