Stylloha

🚀 stylloha

This is a LyCORIS adapter derived from black-forest-labs/FLUX.1-dev, which can be used for text - to - image and image - to - image tasks.

Model Information

Validation Images

You can find some example images in the following gallery:

The main validation prompt used during training was:

A photo-realistic image of a cat

🚀 Quick Start

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.

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

Training settings

• Training epochs: 3
• Training steps: 6000
• Learning rate: 0.0001
  • Learning rate schedule: polynomial
  • Warmup steps: 100
• Max grad value: 2.0
• Effective batch size: 3
  • Micro-batch size: 3
  • 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'])
• Optimizer: adamw_bf16
• Trainable parameter precision: Pure BF16
• Base model precision: no_change
• Caption dropout probability: 0.05%

LyCORIS Config:

{
    "algo": "loha",
    "multiplier": 1.0,
    "linear_dim": 32,
    "linear_alpha": 16,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

styl-256

• Repeats: 10
• Total number of images: 43
• Total number of aspect buckets: 2
• Resolution: 0.065536 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

styl-crop-256

• Repeats: 10
• Total number of images: 43
• Total number of aspect buckets: 1
• Resolution: 0.065536 megapixels
• Cropped: True
• Crop style: center
• Crop aspect: square
• Used for regularisation data: No

styl-512

• Repeats: 10
• Total number of images: 43
• Total number of aspect buckets: 2
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

styl-crop-512

• Repeats: 10
• Total number of images: 43
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: True
• Crop style: center
• Crop aspect: square
• Used for regularisation data: No

styl-768

• Repeats: 10
• Total number of images: 43
• Total number of aspect buckets: 2
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

styl-crop-768

• Repeats: 10
• Total number of images: 43
• Total number of aspect buckets: 1
• Resolution: 0.589824 megapixels
• Cropped: True
• Crop style: center
• Crop aspect: square
• Used for regularisation data: No

styl-1024

• Repeats: 10
• Total number of images: 16
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

💻 Usage Examples

Basic Usage

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 = 'quzo/stylloha'
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 = "A photo-realistic image of a cat"


## 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,
    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")

Advanced Usage

The above code already contains some optional operations for advanced usage, such as model quantization to save VRAM. You can uncomment the relevant code to use these advanced features.

📄 License

This project is under the [other] license.