Marttiini Hirvi Black knife, black handle with bronze ends, dark blade with visible engraving, sheath black leather with J. Marttiini Finland logo stamped at the top and moose engraving below it, bronze-colored blade engraving at the bottom of the sheath, next to the knife, knife resting on moss and lichen, close-up, blurry background

Validation settings

CFG: 7.0
CFG Rescale: 0.7
Steps: 20
Sampler: FlowMatchEulerDiscreteScheduler
Seed: 42
Resolution: 1024x1024
Skip-layer guidance:

Note: The validation settings are not necessarily the same as the training settings.

You can find some example images in the following gallery:

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

Training settings

Training epochs: 0
Training steps: 25000
Learning rate: 0.0005
- Learning rate schedule: cosine
- Warmup steps: 500
Max grad value: 2.0
Effective batch size: 12
- Micro-batch size: 12
- Gradient accumulation steps: 1
- Number of GPUs: 1
Gradient checkpointing: True
Prediction type: flow_matching (extra parameters=['shift=3'])
Optimizer: prodigy
Trainable parameter precision: Pure BF16
Base model precision: int8-quanto
Caption dropout probability: 0.05%

LyCORIS Config:

json

{
    "algo": "lora",
    "multiplier": 1.0,
    "linear_dim": 256,
    "linear_alpha": 256,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 256
            },
            "FeedForward": {
                "factor": 256
            }
        }
    }
}

Datasets

rapala-marttiini-dataset-images

Repeats: 5
Total number of images: 128106
Total number of aspect buckets: 1
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
from lycoris import create_lycoris_from_weights


def download_adapter(repo_id: str):
    import os
    from huggingface_hub import hf_hub_download
    adapter_filename = "pytorch_lora_weights.safetensors"
    cache_dir = os.environ.get('HF_PATH', os.path.expanduser('~/.cache/huggingface/hub/models'))
    cleaned_adapter_path = repo_id.replace("/", "_").replace("\\", "_").replace(":", "_")
    path_to_adapter = os.path.join(cache_dir, cleaned_adapter_path)
    path_to_adapter_file = os.path.join(path_to_adapter, adapter_filename)
    os.makedirs(path_to_adapter, exist_ok=True)
    hf_hub_download(
        repo_id=repo_id, filename=adapter_filename, local_dir=path_to_adapter
    )

    return path_to_adapter_file
    
model_id = 'stabilityai/stable-diffusion-3.5-large'
adapter_repo_id = 'tekoaly4/rapala-marttiini-simpletuner-lora'
adapter_filename = 'pytorch_lora_weights.safetensors'
adapter_file_path = download_adapter(repo_id=adapter_repo_id)
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer)
wrapper.merge_to()

prompt = "Marttiini Hirvi Black knife, black handle with bronze ends, dark blade with visible engraving, sheath black leather with J. Marttiini Finland logo stamped at the top and moose engraving below it, bronze-colored blade engraving at the bottom of the sheath, next to the knife, knife resting on moss and lichen, close-up, blurry background"
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=7.0,
).images[0]

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