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:

Prompt
a psychedelic man is surfing on top of a horse

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: 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")