Mary-Cassatt-Oil-Flux-LoKr-Fast

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

No validation prompt was used during training.

None

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:

Prompt

unconditional (blank prompt)

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt oil painting, A woman in a purple patterned garment holds an unclothed baby who rests against her shoulder, their arm draped over it. The background is rendered in soft, muted green tones with visible pastel strokes.

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt oil painting, A child stands wearing a red velvet outfit with white lace cuffs and a large straw hat with a black ribbon band. Their light-colored hair shows beneath the hat, and their arms are crossed at the waist against a plain, muted background.

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt oil painting, A woman with dark hair wears a blue dress with patterned details, sitting against a green background. A child with curly blonde hair in white leans close as they examine something in the woman's hands.

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt oil painting, A woman in soft colors holds her baby close.

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt oil painting, A child in a blue hat stands by a window.

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt oil painting, Two figures lean together, loosely rendered.

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt oil painting, A mother in casual clothes checks her phone while her baby sleeps against her shoulder, the screen's glow creating soft highlights.

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt oil painting, A woman shows her grandmother how to use a tablet, both faces illuminated by its light against a dark interior.

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt oil painting, A bearded hipster holds his baby while building a chair.

Negative Prompt

blurry, cropped, ugly

Prompt

In the style of a c4ss4tt pastel drawing, A mother hamster grooms her baby hamster in a sunny window.

Negative Prompt

blurry, cropped, ugly

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

Training settings

• Training epochs: 8
• Training steps: 3200
• Learning rate: 0.001
• Max grad norm: 0.1
• Effective batch size: 6
  • Micro-batch size: 6
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: flow-matching (flux parameters=['flux_guidance_value=1.0'])
• Rescaled betas zero SNR: False
• Optimizer: adamw_bf16
• Precision: Pure BF16
• Quantised: Yes: int8-quanto
• 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

cassatt-512

• Repeats: 11
• Total number of images: 49
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

cassatt-768

• Repeats: 11
• Total number of images: 49
• Total number of aspect buckets: 8
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

cassatt-1024

• Repeats: 5
• Total number of images: 49
• Total number of aspect buckets: 10
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

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 = "An astronaut is riding a horse through the jungles of Thailand."

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")