Training epochs: 431
Training steps: 9500
Learning rate: 0.0001
- Learning rate schedule: polynomial
- 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: adamw_bf16
Trainable parameter precision: Pure BF16
Base model precision: int8-quanto
Caption dropout probability: 0.1%
LoRA Rank: 64
LoRA Alpha: 64.0
LoRA Dropout: 0.1
LoRA initialisation style: default
LoRA mode: Standard

Datasets

mayunoha-sd35L

Repeats: 0
Total number of images: 22
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: center
Crop aspect: square
Used for regularisation data: No

Inference

python

import torch
from diffusers import DiffusionPipeline

model_id = 'stabilityai/stable-diffusion-3.5-large'
adapter_id = 'toyssamurai/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 mayunoha woman"
negative_prompt = 'blurry, cropped, ugly'

## 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
model_output = pipeline(
    prompt=prompt,
    negative_prompt=negative_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]

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