Mani Flux Dress

🚀 mani-flux-dress

This is a LyCORIS adapter derived from black-forest-labs/FLUX.1-dev. It is mainly used for text - to - image and image - to - image tasks, offering high - quality image generation capabilities.

🚀 Quick Start

Prerequisites

• Python environment
• Necessary libraries such as torch, diffusers, lycoris, huggingface_hub, etc.

Installation

You need to install relevant libraries according to the requirements of the code. For example:

pip install torch diffusers lycoris huggingface_hub

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 = 'PixelWormhole/mani-flux-dress'
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 film still of a high fashion photoshoot featuring the _8FSL39XP1_ Dress, an elegant off-the-shoulder design in delicate white lace with floral motifs. The dress is form-fitting, mini-length, with long sleeves that flare slightly at the cuffs. The scene is set in a luxurious, modern Mediterranean architectural space with a sea view. A beautiful, young, natural-looking European woman with long hair is captured in a dynamic mid-motion pose, either mid-step or gently turning. She stands against a backdrop of clean white stone and curated designer furniture in neutral tones, with the calm, open sea visible in the distance. Her expression is serene and self-assured, her posture poised and refined. Natural daylight enhances the soft textures and casts gentle shadows across the scene. The color palette blends creamy whites, stone beiges, and hints of ocean blue."


## 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=28,
    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")

✨ Features

• Based on LyCORIS Adapter: Derived from black-forest-labs/FLUX.1-dev, it can generate high - quality images.
• Multiple Image Generation Modes: Support text - to - image and image - to - image generation.
• Customizable Parameters: You can adjust parameters such as CFG, Steps, Sampler, etc. to get different image generation results.

📦 Installation

You need to install relevant libraries according to the requirements of the code. For example:

pip install torch diffusers lycoris huggingface_hub

💻 Usage Examples

Basic Usage

# The above inference code is a basic usage example, which can generate images according to the specified prompt.

Advanced Usage

You can adjust parameters such as lora_scale, prompt, num_inference_steps, etc. to generate different images. For example:

# Change lora_scale
lora_scale = 0.5
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer)
wrapper.merge_to()

# Change prompt
prompt = "A cute kitten in a colorful garden"

model_output = pipeline(
    prompt=prompt,
    num_inference_steps=30,
    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("new_output.png", format="PNG")

📚 Documentation

Validation Settings

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

Training Settings

LyCORIS Config

{
    "algo": "lora",
    "multiplier": 1.0,
    "linear_dim": 64,
    "linear_alpha": 32,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

🔧 Technical Details

This project is a LyCORIS adapter based on black-forest-labs/FLUX.1-dev. It uses the LoRA algorithm for parameter adjustment and training, and can generate high - quality images through the diffusion model. During the training process, parameters such as learning rate, batch size, and gradient checkpointing are set to ensure the stability and efficiency of training.

📄 License

The license is other.