alberto_flux_v3

alberto_flux_v3

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

The main validation prompt used during training was:

The building is a minimalist cube with a stark white façade, emphasizing purity and simplicity in form. Flat surfaces and sharp lines dominate its design, with strategically placed rectangular voids and windows punctuating the clean geometry. The primary material is smooth white plaster, reflecting sunlight to create striking contrasts between light and shadow across the facade. The flat roof and absence of ornamentation further underline the minimalist aesthetic. The surrounding environment includes sparse greenery, which contrasts with the white structure and softens the rigid lines. The sloped street in front adds a dynamic perspective to the otherwise straightforward composition. The building's interaction with natural light plays a pivotal role in highlighting its minimalistic elegance.

Validation settings

• CFG: 3.0
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• Seed: 42
• Resolution: 1024x1024

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: 10
• Training steps: 4500
• Learning rate: 0.0001
• Effective batch size: 1
  • Micro-batch size: 1
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: flow-matching
• Rescaled betas zero SNR: False
• Optimizer: adamw_bf16
• Precision: Pure BF16
• Quantised: No
• Xformers: Not used
• 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

my-dataset-1024

• Repeats: 1
• Total number of images: 209
• Total number of aspect buckets: 8
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'pytorch_lora_weights.safetensors' # you will have to download this manually
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_id, pipeline.transformer)
wrapper.merge_to()

prompt = "The building is a minimalist cube with a stark white façade, emphasizing purity and simplicity in form. Flat surfaces and sharp lines dominate its design, with strategically placed rectangular voids and windows punctuating the clean geometry. The primary material is smooth white plaster, reflecting sunlight to create striking contrasts between light and shadow across the facade. The flat roof and absence of ornamentation further underline the minimalist aesthetic. The surrounding environment includes sparse greenery, which contrasts with the white structure and softens the rigid lines. The sloped street in front adds a dynamic perspective to the otherwise straightforward composition. The building's interaction with natural light plays a pivotal role in highlighting its minimalistic elegance."

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
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(1641421826),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")