---
license: other
base_model: "black-forest-labs/FLUX.1-schnell"
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: ''''
  output:
    url: ./assets/image_0_0.png
- text: 'A happy pizza.'
  parameters:
    negative_prompt: ''''
  output:
    url: ./assets/image_1_0.png
---

# flux-lora-training

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


The main validation prompt used during training was:
```
A happy pizza.
```


## Validation settings
- CFG: `0.0`
- CFG Rescale: `0.0`
- Steps: `15`
- 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: 1
- Training steps: 25
- Learning rate: 0.0001
  - Learning rate schedule: constant_with_warmup
  - Warmup steps: 100
- Max grad norm: 1.0
- Effective batch size: 16
  - Micro-batch size: 2
  - Gradient accumulation steps: 8
  - Number of GPUs: 1
- Gradient checkpointing: True
- Prediction type: flow-matching (extra parameters=['flux_fast_schedule', 'flux_schedule_auto_shift', 'shift=0.0', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flow_matching_loss=compatible', 'flux_lora_target=all+ffs'])
- Optimizer: adamw_bf16
- Trainable parameter precision: Pure BF16
- Caption dropout probability: 0.0%


- LoRA Rank: 16
- LoRA Alpha: None
- LoRA Dropout: 0.1
- LoRA initialisation style: default
    

## Datasets

### default_dataset
- Repeats: 0
- Total number of images: 90
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### default_dataset_512
- Repeats: 0
- Total number of images: 90
- Total number of aspect buckets: 1
- Resolution: 0.262144 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### default_dataset_768
- Repeats: 0
- Total number of images: 90
- Total number of aspect buckets: 1
- Resolution: 0.589824 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-schnell'
adapter_id = 'manbeast3b/flux-lora-training'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "A happy pizza."


## 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=15,
    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=0.0,
).images[0]
image.save("output.png", format="PNG")
```