besch-style-st-flux-lokr-lion-3e-5-bs2-ga3-v04

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

The main validation prompt used during training was:

a striking gothic female vampire with long flowing blonde hair wearing a black sleeveless dress, she has an elegant collar with a vampiric touch giving her a regal yet dangerous appearance, her glowing bright blue eyes emit an ethereal light, bats are flying in the background silhouetted against a neon pink and dark purple sky, the lighting emphasizes her pale skin and shadows accentuate her curves, creating a dark and mystical atmosphere filled with supernatural energy

Validation settings

• CFG: 3.5
• CFG Rescale: 0.0
• Steps: 24
• Sampler: None
• Seed: 42
• Resolution: 768x1344

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

a striking gothic female vampire with long flowing blonde hair wearing a black sleeveless dress, she has an elegant collar with a vampiric touch giving her a regal yet dangerous appearance, her glowing bright blue eyes emit an ethereal light, bats are flying in the background silhouetted against a neon pink and dark purple sky, the lighting emphasizes her pale skin and shadows accentuate her curves, creating a dark and mystical atmosphere filled with supernatural energy

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: 138
• Training steps: 10500
• Learning rate: 3e-05
• Max grad norm: 1.0
• Effective batch size: 6
  • Micro-batch size: 2
  • Gradient accumulation steps: 3
  • Number of GPUs: 1
• Prediction type: flow-matchingNone
• Rescaled betas zero SNR: False
• Optimizer: optimi-lionweight_decay=1e-3
• Precision: Pure BF16
• Quantised: Yes: int8-quanto
• Xformers: Not used
• LyCORIS Config:

{
    "algo": "lokr",
    "multiplier": 1.0,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 12,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "Attention": {
                "factor": 12
            },
            "FeedForward": {
                "factor": 6
            }
        }
    }
}

Datasets

BESCH-V04-512

• Repeats: 1
• Total number of images: 70
• Total number of aspect buckets: 5
• Resolution: 0.262144 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

BESCH-V04-768

• Repeats: 1
• Total number of images: 70
• Total number of aspect buckets: 4
• Resolution: 0.589824 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

BESCH-V04-1024

• Repeats: 1
• Total number of images: 70
• Total number of aspect buckets: 3
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: closest

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 = "a striking gothic female vampire with long flowing blonde hair wearing a black sleeveless dress, she has an elegant collar with a vampiric touch giving her a regal yet dangerous appearance, her glowing bright blue eyes emit an ethereal light, bats are flying in the background silhouetted against a neon pink and dark purple sky, the lighting emphasizes her pale skin and shadows accentuate her curves, creating a dark and mystical atmosphere filled with supernatural energy"

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=24,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=768,
    height=1344,
    guidance_scale=3.5,
).images[0]
image.save("output.png", format="PNG")