metadata

license: creativeml-openrail-m
base_model: stabilityai/stable-diffusion-xl-base-1.0
tags:
  - sdxl
  - sdxl-diffusers
  - text-to-image
  - image-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - lora
  - template:sd-lora
  - standard
pipeline_tag: text-to-image
inference: true

simpletuner

This is a PEFT SingLoRA derived from stabilityai/stable-diffusion-xl-base-1.0.

The main validation prompt used during training was:

A photo-realistic image of a River Phoenix sitting in a field of lavender flowers. The River Phoenix is looking at the viewer.

Validation settings

CFG: 4.2
CFG Rescale: 0.0
Steps: 20
Sampler: ddim
Seed: 42
Resolution: 1024x1024

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

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

Training settings

Training epochs: 0
Training steps: 1
Learning rate: 0.0001
- Learning rate schedule: constant
- Warmup steps: 0
Max grad value: 2.0
Effective batch size: 4
- Micro-batch size: 4
- Gradient accumulation steps: 1
- Number of GPUs: 1
Gradient checkpointing: True
Prediction type: epsilon (extra parameters=['training_scheduler_timestep_spacing=trailing', 'inference_scheduler_timestep_spacing=trailing'])
Optimizer: optimi-stableadamw
Trainable parameter precision: Pure BF16
Base model precision: int8-quanto
Caption dropout probability: 0.1%
LoRA Rank: 16
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default
LoRA mode: SingLoRA

Datasets

subject-1024

Repeats: 4
Total number of images: 29
Total number of aspect buckets: 9
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

subject-512

Repeats: 4
Total number of images: 29
Total number of aspect buckets: 8
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None
Used for regularisation data: No

Inference

import torch
from diffusers import DiffusionPipeline

from peft_singlora import setup_singlora
setup_singlora() # overwrites the nn.Linear mapping in PEFT.
model_id = 'stabilityai/stable-diffusion-xl-base-1.0'
adapter_id = 'bghira/simpletuner'
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 River Phoenix sitting in a field of lavender flowers. The River Phoenix is looking at the viewer."
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.unet, weights=qint8)
freeze(pipeline.unet)
    
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=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=4.2,
    guidance_rescale=0.0,
).images[0]

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