Mary-Cassatt-Oil-Crops-Phase-2-After-Slow-Beta-2-2-4-SS2_0-1536Flux-LoKr

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: 1152x1536

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 seated in a green chair wears a yellow dress with a large sunflower. She holds a mirror in front of a small child sitting on her lap, who is unclothed. Behind them, another mirror reflects their images, adding depth to the setting.

Negative Prompt
blurry, cropped, ugly

Prompt
In the style of a c4ss4tt oil painting, A child stands wearing a red velvet outfit with lace cuffs and a matching hat, holding a stick. The child is accompanied by a small dog at their side. The background is a dark, neutral curtain, and the child is standing on a richly colored carpet.

Negative Prompt
blurry, cropped, ugly

Prompt
In the style of a c4ss4tt oil painting, A woman in faded denim overalls lounges on a rumpled bed beside her young child, who wears striped pajamas. The child leans against her shoulder while they look at a tablet device on a modern side table, next to a mason jar of lemonade. Behind them, a navy blue upholstered headboard stands against a wall with minimalist geometric wallpaper in sage and cream.

Negative Prompt
blurry, cropped, ugly

Prompt
In the style of a c4ss4tt oil painting, A woman in a thick knit sweater dress in autumn rust sits in a cushioned window nook with her young child, who wears fleece footie pajamas. They share a thick quilted blanket while snow falls outside. A wooden side table holds steaming mugs of cocoa and a plate of cookies, while fairy lights twinkle along the window frame against deep purple curtains.

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: 5
Training steps: 3150
Learning rate: 0.0002
Max grad norm: 0.1
Effective batch size: 3
- Micro-batch size: 3
- Gradient accumulation steps: 1
- Number of GPUs: 1
Prediction type: flow-matching (extra parameters=['shift=0.7', 'flux_guidance_value=1.0', 'flux_beta_schedule_alpha=2.0', 'flux_beta_schedule_beta=4.0'])
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-combined-512

Repeats: 11
Total number of images: 25
Total number of aspect buckets: 10
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

cassatt-combined-768

Repeats: 11
Total number of images: 25
Total number of aspect buckets: 11
Resolution: 0.589824 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

cassatt-combined-1024

Repeats: 5
Total number of images: 25
Total number of aspect buckets: 17
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

cassatt-oil-1536

Repeats: 5
Total number of images: 24
Total number of aspect buckets: 17
Resolution: 2.359296 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


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 = 'davidrd123/Mary-Cassatt-Oil-Crops-Phase-2-After-Slow-Beta-2-2-4-SS2_0-1536Flux-LoKr'
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 = "An astronaut is riding a horse through the jungles of Thailand."


## Optional: quantise the model to save on vram.
## Note: The model was quantised during training, and so it is recommended to do the same 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
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=1152,
    height=1536,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")

davidrd123
/

Mary-Cassatt-Oil-Crops-Phase-2-After-Slow-Beta-2-2-4-SS2_0-1536Flux-LoKr