Training epochs: 43
Training steps: 13200
Learning rate: 1e-06
Effective batch size: 16
- Micro-batch size: 1
- Gradient accumulation steps: 16
- Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: adamw_bf16
Precision: Pure BF16
Quantised: Yes: int8-quanto
Xformers: Not used
LyCORIS Config:

json

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 1000000,
    "linear_alpha": 1,
    "factor": 10,
    "full_matrix": true,
    "apply_preset": {
        "target_module": [
            "FluxTransformerBlock",
            "FluxSingleTransformerBlock"
        ],
        "name_algo_map": {
            "transformer_blocks.[0-7].ff*": {
                "algo": "lokr",
                "factor": 4,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[0-7]*": {
                "algo": "lokr",
                "factor": 8,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[8-15].ff*": {
                "algo": "lokr",
                "factor": 6,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[8-15]*": {
                "algo": "lokr",
                "factor": 12,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[16-18].ff*": {
                "algo": "lokr",
                "factor": 12,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[16-18]*": {
                "algo": "lokr",
                "factor": 24,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[0-15].ff*": {
                "algo": "lokr",
                "factor": 8,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[0-15]*": {
                "algo": "lokr",
                "factor": 16,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[16-23].ff*": {
                "algo": "lokr",
                "factor": 6,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[16-23]*": {
                "algo": "lokr",
                "factor": 12,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[24-37].ff*": {
                "algo": "lokr",
                "factor": 4,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[24-37]*": {
                "algo": "lokr",
                "factor": 8,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            }
        },
        "use_fnmatch": true
    }
}

Datasets

default_dataset_arb1

Repeats: 0
Total number of images: 68
Total number of aspect buckets: 12
Resolution: 1.5 megapixels
Cropped: False
Crop style: None
Crop aspect: None

default_dataset_arb_2

Repeats: 0
Total number of images: 67
Total number of aspect buckets: 1
Resolution: 1.6384 megapixels
Cropped: True
Crop style: random
Crop aspect: closest

default_dataset_arb_3

Repeats: 0
Total number of images: 67
Total number of aspect buckets: 1
Resolution: 2.166784 megapixels
Cropped: True
Crop style: random
Crop aspect: closest

default_dataset_arb3

Repeats: 0
Total number of images: 2341
Total number of aspect buckets: 42
Resolution: 1.5 megapixels
Cropped: False
Crop style: None
Crop aspect: None

default_dataset_arb4

Repeats: 0
Total number of images: 3155
Total number of aspect buckets: 36
Resolution: 1.0 megapixels
Cropped: False
Crop style: None
Crop aspect: None

default_dataset_art

Repeats: 0
Total number of images: 2482
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_crops

Repeats: 0
Total number of images: 42
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: random
Crop aspect: closest

default_dataset

Repeats: 0
Total number of images: 42
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_768

Repeats: 0
Total number of images: 42
Total number of aspect buckets: 1
Resolution: 0.589824 megapixels
Cropped: True
Crop style: center
Crop aspect: square

default_dataset_896

Repeats: 0
Total number of images: 42
Total number of aspect buckets: 1
Resolution: 0.802816 megapixels
Cropped: True
Crop style: center
Crop aspect: square

Inference

python

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 = "loona from helluva boss is eating a donut"

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=15,
    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")

jimmycarter/flux-training-losercity-next-lycoris14

flux-training-losercity-next-lycoris14

Validation settings

Training settings

Datasets

default_dataset_arb1

default_dataset_arb_2

default_dataset_arb_3

default_dataset_arb3

default_dataset_arb4

default_dataset_art

default_dataset_crops

default_dataset

default_dataset_768

default_dataset_896

Inference

jimmycarter/
flux-training-losercity-next-lycoris14