README.md

metadata

license: other
base_model: stabilityai/stable-diffusion-3.5-large
tags:
  - sd3
  - sd3-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - safe-for-work
  - lora
  - template:sd-lora
  - standard
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: sweatshirt painted in the alebrijeros style
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png

sd3-lora-alebrijeros-final

This is a standard PEFT LoRA derived from stabilityai/stable-diffusion-3.5-large.

The main validation prompt used during training was:

sweatshirt painted in the alebrijeros style

Validation settings

• CFG: 5.0
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• Seed: 42
• Resolution: 512x512

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

You can find some example images in the following gallery:

Prompt

grey shirt with a small logo of a bunny painted in the alebrijeros style

Prompt

hoodie with flowers painted in the alebrijeros style

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

Training settings

• Training epochs: 4
• Training steps: 2470
• Learning rate: 5e-05
• 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
• LoRA Rank: 64
• LoRA Alpha: None
• LoRA Dropout: 0.1
• LoRA initialisation style: default

Datasets

alebrijeros-dataset-final-512

• Repeats: 5
• Total number of images: 25
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

alebrijeros-dataset-final-1024

• Repeats: 5
• Total number of images: 25
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None
• Used for regularisation data: No

alebrijeros-dataset-final-512-crop

• Repeats: 5
• Total number of images: 25
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square
• Used for regularisation data: No

alebrijeros-dataset-final-1024-crop

• Repeats: 5
• Total number of images: 25
• 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

model_id = 'stabilityai/stable-diffusion-3.5-large'
adapter_id = 'CarlosRiverMe/sd3-lora-alebrijeros-final'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "sweatshirt painted in the alebrijeros style"
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=512,
    height=512,
    guidance_scale=5.0,
).images[0]
image.save("output.png", format="PNG")