bghira / sd3-lora-test

sd3-lora-test

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

The main validation prompt used during training was:

a psychedelic man is surfing on top of a horse

Validation settings

• CFG: 5.0
• CFG Rescale: 0.2
• Steps: 50
• Sampler: euler
• Seed: 2
• Resolution: 1280x768

Note: The validation settings are not necessarily the same as the training settings .

You can find some example images in the following gallery:

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

Training settings

• Training epochs: 0
• Training steps: 100
• Learning rate: 1e-06
• Effective batch size: 1
  • Micro-batch size: 1
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: v_prediction
• Rescaled betas zero SNR: True
• Optimizer: AdamW, stochastic bf16
• Precision: Pure BF16
• Xformers: Not used
• LoRA Rank: 16
• LoRA Alpha: 16
• LoRA Dropout: 0.1
• LoRA initialisation style: default

Datasets

celebrities

• Repeats: 0
• Total number of images: 1253
• Total number of aspect buckets: 3
• Resolution: 1.0 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: random

Inference

import torchfrom diffusers import StableDiffusion3Pipeline


model_id = "sd3-lora-test"
prompt = "a psychedelic man is surfing on top of a horse"
negative_prompt = "malformed, disgusting, overexposed, washed-out"

pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    negative_prompt='blurry, cropped, ugly',
    num_inference_steps=50,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1152,
    height=768,
    guidance_scale=5.0,
    guidance_rescale=0.2,
).images[0]
image.save(f"output.png", format="PNG")