bghira/sd35m-sfwbooru-lokr

sd35m-sfwbooru-lokr

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

The main validation prompt used during training was:

A photo-realistic image of a cat

Validation settings

• —CFG: 3.2
• —CFG Rescale: 0.0
• —Steps: 30
• —Sampler: FlowMatchEulerDiscreteScheduler
• —Seed: 42
• —Resolution: 1024x1024
• —Skip-layer guidance: skipguidancelayers=[7, 8, 9],

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

You can find some example images in the following gallery:

<Gallery />

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

Training settings

• —Training epochs: 4
• —Training steps: 264250
• —Learning rate: 1.0
• —Learning rate schedule: cosine
• —Warmup steps: 500000
• —Max grad value: 0.0
• —Effective batch size: 6
• —Micro-batch size: 6
• —Gradient accumulation steps: 1
• —Number of GPUs: 1
• —Gradient checkpointing: True
• —Prediction type: flow-matching (extra parameters=['shift=3'])
• —Optimizer: prodigyd0=1e-8,eps=1e-8
• —Trainable parameter precision: Pure BF16
• —Base model precision: no_change
• —Caption dropout probability: 10.0%

• —LoRA Rank: 16
• —LoRA Alpha: None
• —LoRA Dropout: 0.1
• —LoRA initialisation style: default

Datasets

sfwbooru-crop

• —Repeats: 0
• —Total number of images: 363920
• —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-medium'
adapter_id = 'bghira/sd35m-sfwbooru-lokr'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "A photo-realistic image of a cat"
negative_prompt = 'blurry, cropped, ugly'

## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it 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
model_output = pipeline(
    prompt=prompt,
    negative_prompt=negative_prompt,
    num_inference_steps=30,
    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=3.2,
    skip_guidance_layers=[7, 8, 9],
).images[0]

model_output.save("output.png", format="PNG")

Exponential Moving Average (EMA)

SimpleTuner generates a safetensors variant of the EMA weights and a pt file.

The safetensors file is intended to be used for inference, and the pt file is for continuing finetuning.

The EMA model may provide a more well-rounded result, but typically will feel undertrained compared to the full model as it is a running decayed average of the model weights.