0211

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

The main validation prompt used during training was:

A pixel art sprite of majestic water and dark-element cat. It evolved for full, featuring slender graceful body. The cat has sleek, shadowy black fur with glowing blue wave-like patterns flowing across its body. Its piercing blue eyes glow with an ethereal light, and its tail curls in a spiral, resembling a dark water vortex. Small floating water droplets and ghostly blue mist surround the cat, enhancing its mysterious aura. The background is dark to contrast the bright neon blue elements, with pixelated waves and shadowy mist effects. Created using high-detail pixel art, vibrant color balance, and dynamic lighting effects.

Validation settings

CFG: 5.0
CFG Rescale: 0.0
Steps: 20
Sampler: FlowMatchEulerDiscreteScheduler
Seed: 42
Resolution: 1024x1024
Skip-layer guidance:

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

Prompt
A pixel art sprite of majestic water and dark-element cat. It evolved for full, featuring slender graceful body. The cat has sleek, shadowy black fur with glowing blue wave-like patterns flowing across its body. Its piercing blue eyes glow with an ethereal light, and its tail curls in a spiral, resembling a dark water vortex. Small floating water droplets and ghostly blue mist surround the cat, enhancing its mysterious aura. The background is dark to contrast the bright neon blue elements, with pixelated waves and shadowy mist effects. Created using high-detail pixel art, vibrant color balance, and dynamic lighting effects.

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: 8
Training steps: 10000
Learning rate: 8e-05
- Learning rate schedule: polynomial
- Warmup steps: 100
Max grad norm: 2.0
Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
Gradient checkpointing: True
Prediction type: flow-matching (extra parameters=['shift=3'])
Optimizer: adamw_bf16
Trainable parameter precision: Pure BF16
Caption dropout probability: 5.0%
LoRA Rank: 64
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

dataset-1024

Repeats: 10
Total number of images: 53
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

dataset-crop-1024

Repeats: 10
Total number of images: 53
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: True
Crop style: center
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 = 'badul13/0211'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "A pixel art sprite of majestic water and dark-element cat. It evolved for full, featuring slender graceful body. The cat has sleek, shadowy black fur with glowing blue wave-like patterns flowing across its body. Its piercing blue eyes glow with an ethereal light, and its tail curls in a spiral, resembling a dark water vortex. Small floating water droplets and ghostly blue mist surround the cat, enhancing its mysterious aura. The background is dark to contrast the bright neon blue elements, with pixelated waves and shadowy mist effects. Created using high-detail pixel art, vibrant color balance, and dynamic lighting effects."
negative_prompt = 'blurry, cropped, ugly'

## Optional: quantise the model to save on vram.
## Note: The model was quantised during training, and so it is recommended to do the same during inference time.
from optimum.quanto import quantize, freeze, qint8
quantize(pipeline.transformer, weights=qint8)
freeze(pipeline.transformer)
    
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
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(42),
    width=1024,
    height=1024,
    guidance_scale=5.0,
).images[0]
image.save("output.png", format="PNG")

badul13
/

0211