---
license: other
base_model: "black-forest-labs/FLUX.1-dev"
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - lora
  - template:sd-lora
  - standard
inference: true
widget:
- text: 'unconditional (blank prompt)'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'
  output:
    url: ./assets/image_0_0.png
- text: 'An expressive, hand-drawn illustration depicting soldiers and tanks in a surreal, dreamlike battlefield. The scene features bold, textured linework and vibrant, contrasting colors, with exaggerated proportions and fantastical details. The tanks appear slightly distorted, almost alive, while the soldiers are portrayed with whimsical, otherworldly features, blending realism with a sense of unease. The background includes dramatic skies, rugged terrain, and dynamic lighting, creating a poetic yet slightly eerie atmosphere in a graphic novel style'
  parameters:
    negative_prompt: 'blurry, cropped, ugly'
  output:
    url: ./assets/image_1_0.png
---

# maver1chh/allart

This is a standard PEFT LoRA 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:
```
An expressive, hand-drawn illustration depicting soldiers and tanks in a surreal, dreamlike battlefield. The scene features bold, textured linework and vibrant, contrasting colors, with exaggerated proportions and fantastical details. The tanks appear slightly distorted, almost alive, while the soldiers are portrayed with whimsical, otherworldly features, blending realism with a sense of unease. The background includes dramatic skies, rugged terrain, and dynamic lighting, creating a poetic yet slightly eerie atmosphere in a graphic novel style
```


## 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).

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: 6
- Training steps: 8000
- Learning rate: 0.0003
  - Learning rate schedule: polynomial
  - Warmup steps: 100
- Max grad norm: 1.0
- Effective batch size: 1
  - Micro-batch size: 1
  - Gradient accumulation steps: 1
  - 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: 16
- LoRA Alpha: 16.0
- LoRA Dropout: 0.1
- LoRA initialisation style: default
    

## Datasets

### allbrook-512
- Repeats: 10
- Total number of images: 36
- Total number of aspect buckets: 1
- Resolution: 0.262144 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### allbrook-768
- Repeats: 10
- Total number of images: 36
- Total number of aspect buckets: 11
- Resolution: 0.589824 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### allbrook-1024
- Repeats: 10
- Total number of images: 36
- Total number of aspect buckets: 11
- Resolution: 1.048576 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No


## Inference


```python
import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'maver1chh/maver1chh/allart'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "An expressive, hand-drawn illustration depicting soldiers and tanks in a surreal, dreamlike battlefield. The scene features bold, textured linework and vibrant, contrasting colors, with exaggerated proportions and fantastical details. The tanks appear slightly distorted, almost alive, while the soldiers are portrayed with whimsical, otherworldly features, blending realism with a sense of unease. The background includes dramatic skies, rugged terrain, and dynamic lighting, creating a poetic yet slightly eerie atmosphere in a graphic novel style"


## 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")
```