Training epochs: 6
Training steps: 200
Learning rate: 0.0001
Effective batch size: 160
- Micro-batch size: 2
- Gradient accumulation steps: 40
- Number of GPUs: 2
Prediction type: epsilon
Rescaled betas zero SNR: False
Optimizer: AdamW, stochastic bf16
Precision: Pure BF16
Xformers: Enabled

Datasets

4o-training-images-thinned

Repeats: 0
Total number of images: ~4960
Total number of aspect buckets: 1
Resolution: 1.0 megapixels
Cropped: True
Crop style: center
Crop aspect: square

Inference

python

import torch
from diffusers import DiffusionPipeline

model_id = 'pixart-sigma-test'
pipeline = DiffusionPipeline.from_pretrained(model_id)

prompt = "Digital art of a topless anthro male wolf wearing a sun hat and blue banana-patterned swimming trunks"
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='blurry, cropped, ugly',
    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(1641421826),
    width=1152,
    height=768,
    guidance_scale=7.5,
    guidance_rescale=0.0,
).images[0]
image.save("output.png", format="PNG")

bananapuncakes/pixart-sigma-test

pixart-sigma-test

Validation settings

Training settings

Datasets

4o-training-images-thinned

Inference

bananapuncakes/
pixart-sigma-test