sd35-training-m-init

sd35-training-m-init

This is a LyCORIS adapter derived from stabilityai/stable-diffusion-3.5-medium.

The main validation prompt used during training was:

loona from helluva boss.

Validation settings

• CFG: 5.5
• 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: 11
• Training steps: 20000
• Learning rate: 1e-06
• Max grad norm: 0.01
• Effective batch size: 1
  • Micro-batch size: 1
  • Gradient accumulation steps: 1
  • 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:

{
    "bypass_mode": true,
    "algo": "lokr",
    "multiplier": 1.0,
    "full_matrix": true,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 12,
    "apply_preset": {
        "target_module": [
            "JointTransformerBlock"
        ],
        "module_algo_map": {
            "FeedForward": {
                "factor": 1
            },
            "JointTransformerBlock": {
                "factor": 2
            }
        }
    }
}

Datasets

default_dataset_art

• Repeats: 0
• Total number of images: 1805
• Total number of aspect buckets: 374
• Resolution: 2048 px
• Cropped: True
• Crop style: random
• Crop aspect: closest
• Used for regularisation data: No

Inference

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights

model_id = 'stabilityai/stable-diffusion-3.5-medium'
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."
negative_prompt = ''
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=5.5,
).images[0]
image.save("output.png", format="PNG")