Training epochs: 0
Training steps: 8000
Learning rate: 4e-05
- Learning rate schedule: constant
- Warmup steps: 100
Max grad value: 2.0
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'])
Optimizer: optimi-lion
Trainable parameter precision: Pure BF16
Base model precision: no_change
Caption dropout probability: 0.1%
LoRA Rank: 16
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default
LoRA mode: Standard

Datasets

pseudo-camera-10k-pixart

Repeats: 0
Total number of images: 14093
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: random
Crop aspect: square
Used for regularisation data: No

Inference

python

import torch
from diffusers import DiffusionPipeline

model_id = 'fal/AuraFlow-v0.3'
adapter_id = 'amitbcp/simpletuner-lora'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "A photo-realistic image of a cat"
negative_prompt = 'blurry, cropped, ugly'

## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it 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
model_output = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=30,
    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=2.0,
).images[0]

model_output.save("output.png", format="PNG")

Exponential Moving Average (EMA)

SimpleTuner generates a safetensors variant of the EMA weights and a pt file.

The safetensors file is intended to be used for inference, and the pt file is for continuing finetuning.

The EMA model may provide a more well-rounded result, but typically will feel undertrained compared to the full model as it is a running decayed average of the model weights.