playerzer0x/sndyokly_concepts_lycoris_b1_optimi-stableadamw_2e-04_20241021_173335

growwithdaisy/sndyoklyconceptslycorisb1optimi-stableadamw2e-0420241021_173335

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

The main validation prompt used during training was:

photo of a btytthtthn woman wearing oklyflkxl sunglasses

Validation settings

• —CFG: 3.5
• —CFG Rescale: 0.0
• —Steps: 20
• —Sampler: None
• —Seed: 69
• —Resolution: 1024x1024

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

<Gallery />

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

Training settings

• —Training epochs: 73
• —Training steps: 10000
• —Learning rate: 0.0002
• —Max grad norm: 2.0
• —Effective batch size: 1
• —Micro-batch size: 1
• —Gradient accumulation steps: 1
• —Number of GPUs: 1
• —Prediction type: flow-matching (flux parameters=['shift=0.5', 'fluxguidancevalue=1.0'])
• —Rescaled betas zero SNR: False
• —Optimizer: optimi-stableadamwweight_decay=1e-3
• —Precision: Pure BF16
• —Quantised: No
• —Xformers: Not used
• —LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1,
    "linear_dim": 1000000,
    "linear_alpha": 1,
    "factor": 16,
    "init_lokr_norm": 0.001,
    "apply_preset": {
        "target_module": [
            "FluxTransformerBlock",
            "FluxSingleTransformerBlock"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 16
            },
            "FeedForward": {
                "factor": 8
            }
        }
    }
}

Datasets

btythtthn_woman-512

• —Repeats: 0
• —Total number of images: 214
• —Total number of aspect buckets: 7
• —Resolution: 0.262144 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

btythtthn_woman-768

• —Repeats: 0
• —Total number of images: 193
• —Total number of aspect buckets: 8
• —Resolution: 0.589824 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

btythtthn_woman-1024

• —Repeats: 0
• —Total number of images: 138
• —Total number of aspect buckets: 8
• —Resolution: 1.048576 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

oklyflkxl_sunglasses-512

• —Repeats: 1
• —Total number of images: 106
• —Total number of aspect buckets: 11
• —Resolution: 0.262144 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

oklyflkxl_sunglasses-768

• —Repeats: 1
• —Total number of images: 86
• —Total number of aspect buckets: 10
• —Resolution: 0.589824 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

oklyflkxl_sunglasses-1024

• —Repeats: 1
• —Total number of images: 65
• —Total number of aspect buckets: 11
• —Resolution: 1.048576 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

sndylngkim_veil-512

• —Repeats: 1
• —Total number of images: 24
• —Total number of aspect buckets: 5
• —Resolution: 0.262144 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

sndylngkim_veil-768

• —Repeats: 1
• —Total number of images: 22
• —Total number of aspect buckets: 5
• —Resolution: 0.589824 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

sndylngkim_veil-1024

• —Repeats: 1
• —Total number of images: 20
• —Total number of aspect buckets: 5
• —Resolution: 1.048576 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

sndylngrctl_bows-512

• —Repeats: 1
• —Total number of images: 45
• —Total number of aspect buckets: 8
• —Resolution: 0.262144 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

sndylngrctl_bows-768

• —Repeats: 1
• —Total number of images: 33
• —Total number of aspect buckets: 8
• —Resolution: 0.589824 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

sndylngrctl_bows-1024

• —Repeats: 1
• —Total number of images: 25
• —Total number of aspect buckets: 5
• —Resolution: 1.048576 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

sndylngwing_clips-512

• —Repeats: 1
• —Total number of images: 72
• —Total number of aspect buckets: 6
• —Resolution: 0.262144 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

sndylngwing_clips-768

• —Repeats: 1
• —Total number of images: 30
• —Total number of aspect buckets: 5
• —Resolution: 0.589824 megapixels
• —Cropped: False
• —Crop style: None
• —Crop aspect: None
• —Used for regularisation data: No

sndylngwing_clips-1024

• —Repeats: 1
• —Total number of images: 28
• —Total number of aspect buckets: 4
• —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 = "photo of a btytthtthn woman wearing oklyflkxl sunglasses"

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=3.5,
).images[0]
image.save("output.png", format="PNG")