pixart-sigma-test

pixart-sigma-test

This is a full rank finetune derived from PixArt-alpha/PixArt-Sigma-XL-2-1024-MS.

The main validation prompt used during training was:

Digital art of a topless anthro male wolf wearing a sun hat and blue banana-patterned swimming trunks

Validation settings

• CFG: 7.5
• CFG Rescale: 0.0
• Steps: 30
• Sampler: None
• Seed: 42
• Resolution: 1024

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: 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

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")