simpletuner-lora

This is a LyCORIS adapter derived from stabilityai/stable-diffusion-3-medium-diffusers.

The main validation prompt used during training was:

A plate of fried calamari with a lemon wedge and a side of green beans, served in a basket with a pink bowl of marinara sauce. The basket is sitting on a table with a checkered tablecloth. In the background is a glass of water and a plate with a burger and fries. The style of the image is a photograph.

Validation settings

• CFG: 3.0
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• Seed: 42
• Resolutions: 1024x1024,1280x768

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
• Effective batch size: 36
  • Micro-batch size: 6
  • Gradient accumulation steps: 1
  • Number of GPUs: 6
• Prediction type: flow-matching
• Rescaled betas zero SNR: False
• Optimizer: adamw_bf16
• Precision: Pure BF16
• Quantised: No
• 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

pseudo-camera-10k-sd3

• Repeats: 0
• Total number of images: ~63978
• Total number of aspect buckets: 1
• Resolution: 1.0 megapixels
• Cropped: True
• Crop style: center
• Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'stabilityai/stable-diffusion-3-medium-diffusers'
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 plate of fried calamari with a lemon wedge and a side of green beans, served in a basket with a pink bowl of marinara sauce. The basket is sitting on a table with a checkered tablecloth. In the background is a glass of water and a plate with a burger and fries. The style of the image is a photograph."
negative_prompt = 'blurry, cropped, ugly'
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    negative_prompt=negative_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")