sd3_egg_lora_rank64_v2

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

The main validation prompt used during training was:

e4g4, A pet egg wrapped in moss and plant essence, resembling a Pokémon game item, on a white background, in the style of Ken Sugimori vector art.

Validation settings

CFG: 5.0
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:

Prompt
unconditional (blank prompt)

Negative Prompt
blurry, cropped, ugly, creature

Prompt
e4g4, A pet egg wrapped in moss and plant essence, resembling a Pokémon game item, on a white background, in the style of Ken Sugimori vector art.

Negative Prompt
blurry, cropped, ugly, creature

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

Training settings

Training epochs: 41
Training steps: 1000
Learning rate: 0.0001
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: bf16
Quantised: No
Xformers: Not used
LoRA Rank: 64
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

sd3_egg

Repeats: 1
Total number of images: 12
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: center
Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'stabilityai/stable-diffusion-3-medium-diffusers'
adapter_id = 'zwloong/sd3_egg_lora_rank64_v2'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "e4g4, A pet egg wrapped in moss and plant essence, resembling a Pokémon game item, on a white background, in the style of Ken Sugimori vector art."
negative_prompt = 'blurry, cropped, ugly, creature'
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=5.0,
).images[0]
image.save("output.png", format="PNG")