simpletuner-lora

simpletuner-lora

This is a LyCORIS adapter derived from black-forest-labs/FLUX.1-dev.

The main validation prompt used during training was:

In the image, PhongKamy is posed in a relaxed manner, conveying a sense of calm and confidence. He is wearing a crisp white shirt that contrasts nicely against his darker pants. The shirt has a classic collar and is unbuttoned at the top, giving it a casual yet polished look. PhongKamy's dark hair is neatly styled, with a slight wave, enhancing his youthful appearance. He is seated with one leg crossed over the other, and he holds a pair of clear, stylish glasses in one hand, suggesting a thoughtful demeanor. His smile is warm and inviting, reflecting a friendly personality. The background is a soft gray, which allows PhongKamy to stand out as the focal point of the image. The lighting is soft and diffused, creating a flattering effect on his features and adding to the overall serene atmosphere of the portrait.

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.

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: 0
• Training steps: 10000
• Learning rate: 0.0001
  • 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'])
• Optimizer: adamw_bf16
• Trainable parameter precision: Pure BF16
• Caption dropout probability: 10.0%

LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 16,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

behitek-subject

• Repeats: 1000
• 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

behitek-subject-512

• Repeats: 1000
• Total number of images: 22
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: True
• Crop style: center
• Crop aspect: square
• Used for regularisation data: No

Inference

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 = 'black-forest-labs/FLUX.1-dev'
adapter_repo_id = 'phongmt184172/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 = "In the image, PhongKamy is posed in a relaxed manner, conveying a sense of calm and confidence. He is wearing a crisp white shirt that contrasts nicely against his darker pants. The shirt has a classic collar and is unbuttoned at the top, giving it a casual yet polished look. PhongKamy's dark hair is neatly styled, with a slight wave, enhancing his youthful appearance. He is seated with one leg crossed over the other, and he holds a pair of clear, stylish glasses in one hand, suggesting a thoughtful demeanor. His smile is warm and inviting, reflecting a friendly personality. The background is a soft gray, which allows PhongKamy to stand out as the focal point of the image. The lighting is soft and diffused, creating a flattering effect on his features and adding to the overall serene atmosphere of the portrait."


## 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")