simpletuner-lora

This is a LyCORIS adapter derived from flux/unknown-model.

The main validation prompt used during training was:

a high-resolution photograph featuring a young asian woman with long, straight, dark brown hair and fair skin, she has a delicate, symmetrical face with large, almond-shaped eyes, full lips, and a slight smile, her expression is calm and inviting, she is dressed in a black, off-the-shoulder dress with a deep v-neckline that accentuates her ample breasts, the dress is made of a soft, velvet-like material that clings to her curves, and it is draped over her shoulders in a gray, abstract patterned shawl, she wears a black choker with a small black ribbon and a black bracelet on her left wrist, her right hand is adorned with a gold ring, and she is holding a small, gold-colored object in her left hand, the background features a modern, minimalist setting with concrete structures and a few decorative boxes with the word chagee written on them, the overall ambiance is serene and sophisticated, with a hint of natural beauty

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.

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

Training settings

• Training epochs: 0
• Training steps: 10001
• Learning rate: 0.0001
• Max grad norm: 1.0
• Effective batch size: 1
  • Micro-batch size: 1
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: flow-matching (flux parameters=['shift=3', 'flux_guidance_value=1.0'])
• 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

xhs_minidata-512

• Repeats: 10
• Total number of images: 560
• Total number of aspect buckets: 9
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

xhs_minidata-1024

• Repeats: 10
• Total number of images: 560
• Total number of aspect buckets: 15
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

xhs_minidata-512-crop

• Repeats: 10
• Total number of images: 560
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square
• Used for regularisation data: No

xhs_minidata-1024-crop

• Repeats: 10
• Total number of images: 560
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square
• Used for regularisation data: No

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = '/data/swh/hub_model/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 high-resolution photograph featuring a young asian woman with long, straight, dark brown hair and fair skin, she has a delicate, symmetrical face with large, almond-shaped eyes, full lips, and a slight smile, her expression is calm and inviting, she is dressed in a black, off-the-shoulder dress with a deep v-neckline that accentuates her ample breasts, the dress is made of a soft, velvet-like material that clings to her curves, and it is draped over her shoulders in a gray, abstract patterned shawl, she wears a black choker with a small black ribbon and a black bracelet on her left wrist, her right hand is adorned with a gold ring, and she is holding a small, gold-colored object in her left hand, the background features a modern, minimalist setting with concrete structures and a few decorative boxes with the word chagee written on them, the overall ambiance is serene and sophisticated, with a hint of natural beauty"

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")