flux-training

flux-training

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

The main validation prompt used during training was:

A figurine of a character with green hair, wearing a white shirt, a black vest, and a gray cap, sitting with one hand on their knee and the other hand making a peace sign. The character is wearing a blue pendant and has a gold bracelet. In the background, there are green plants and a tree branch.

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: 0
• Training steps: 158000
• Learning rate: 5e-06
• Effective batch size: 5
  • Micro-batch size: 1
  • Gradient accumulation steps: 1
  • Number of GPUs: 5
• Prediction type: flow-matching
• 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": 1000000,
    "linear_alpha": 1,
    "factor": 2,
    "full_matrix": true,
    "apply_preset": {
        "name_algo_map": {
            "transformer_blocks.[0-7]*": {
                "algo": "lokr",
                "factor": 4,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[8-15]*": {
                "algo": "lokr",
                "factor": 5,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "transformer_blocks.[16-18]*": {
                "algo": "lokr",
                "factor": 10,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[0-15]*": {
                "algo": "lokr",
                "factor": 8,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[16-23]*": {
                "algo": "lokr",
                "factor": 5,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "full_matrix": true
            },
            "single_transformer_blocks.[24-37]*": {
                "algo": "lokr",
                "factor": 4,
                "linear_dim": 1000000,
                "linear_alpha": 1,
                "use_scalar": true,
                "full_matrix": true
            }
        },
        "use_fnmatch": true
    }
}

Datasets

default_dataset_arb

• Repeats: 0
• Total number of images: ~39950
• Total number of aspect buckets: 6
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

default_dataset_arb2

• Repeats: 0
• Total number of images: ~40005
• Total number of aspect buckets: 6
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

default_dataset_arb3

• Repeats: 0
• Total number of images: ~64080
• Total number of aspect buckets: 6
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

default_dataset_arb4

• Repeats: 0
• Total number of images: ~70340
• Total number of aspect buckets: 6
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

default_dataset_arb5

• Repeats: 0
• Total number of images: ~31790
• Total number of aspect buckets: 6
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

default_dataset_arb6

• Repeats: 0
• Total number of images: ~22035
• Total number of aspect buckets: 5
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

default_dataset_arb7

• Repeats: 0
• Total number of images: ~39390
• Total number of aspect buckets: 6
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

default_dataset

• Repeats: 0
• Total number of images: ~121070
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

default_dataset2

• Repeats: 0
• Total number of images: ~123100
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

default_dataset3

• Repeats: 0
• Total number of images: ~64355
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

default_dataset4

• Repeats: 0
• Total number of images: ~69970
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

default_dataset5

• Repeats: 0
• Total number of images: ~32300
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

default_dataset6

• Repeats: 0
• Total number of images: ~22190
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

default_dataset7

• Repeats: 0
• Total number of images: ~39560
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'black-forest-labs/FLUX.1-schnell'
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 = "A figurine of a character with green hair, wearing a white shirt, a black vest, and a gray cap, sitting with one hand on their knee and the other hand making a peace sign. The character is wearing a blue pendant and has a gold bracelet. In the background, there are green plants and a tree branch."

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")