Simpletuner Lora

🚀 simpletuner-lora

This is a LyCORIS adapter for text-to-image generation. It's derived from stabilityai/stable-diffusion-3.5-medium, offering enhanced capabilities for generating high - quality images.

🚀 Quick Start

This LyCORIS adapter is based on the stabilityai/stable-diffusion-3.5-medium model. The main validation prompt used during training was:

A photo-realistic image of a cat

✨ Features

• Based on Stable Diffusion 3.5 Medium: Leverages the power of the base model for high - quality image generation.
• LyCORIS Adapter: Enhances the model's performance with a LyCORIS adapter.
• Multiple Image Generation Modes: Supports text - to - image and image - to - image generation.

📦 Installation

No specific installation steps are provided in the original README. If you want to use this adapter, you need to have the necessary dependencies installed, such as torch, diffusers, and lycoris.

💻 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 = 'stabilityai/stable-diffusion-3.5-medium'
adapter_repo_id = 'hmwhwm/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 = "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=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=4.0,
    skip_guidance_layers=[7, 8, 9],
).images[0]

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

📚 Documentation

Validation settings

• CFG: 4.0
• CFG Rescale: 0.0
• Steps: 20
• Sampler: FlowMatchEulerDiscreteScheduler
• Seed: 42
• Resolution: 1024x1024
• Skip - layer guidance: skip_guidance_layers=[7, 8, 9]

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

You can find some example images in the following gallery:

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