metadata

license: openrail++
base_model: terminusresearch/pixart-900m-1024-ft-v0.6
tags:
  - pixart_sigma
  - pixart_sigma-diffusers
  - text-to-image
  - image-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - lora
  - controlnet
  - template:sd-lora
  - standard
pipeline_tag: text-to-image
inference: true
widget:
  - text: A photo-realistic image of a cat
    parameters:
      negative_prompt: ugly, cropped, blurry, low-quality, mediocre average
    output:
      url: ./assets/image_0_0.png

pixart-controlnet-lora-test

This is a ControlNet PEFT LoRA derived from terminusresearch/pixart-900m-1024-ft-v0.6.

The main validation prompt used during training was:

A photo-realistic image of a cat

Validation settings

CFG: 4.0
CFG Rescale: 0.0
Steps: 16
Sampler: ddim
Seed: 42
Resolution: 1024x1024

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

You can find some example images in the following gallery:

Prompt
A photo-realistic image of a cat

Negative Prompt
ugly, cropped, blurry, low-quality, mediocre average

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

Training settings

Training epochs: 224
Training steps: 450
Learning rate: 0.0001
- Learning rate schedule: constant
- Warmup steps: 500
Max grad value: 0.01
Effective batch size: 3
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 3
Gradient checkpointing: False
Prediction type: epsilon (extra parameters=['training_scheduler_timestep_spacing=trailing', 'inference_scheduler_timestep_spacing=trailing', 'controlnet_enabled'])
Optimizer: adamw_bf16
Trainable parameter precision: Pure BF16
Base model precision: no_change
Caption dropout probability: 0.0%
LoRA Rank: 64
LoRA Alpha: 64.0
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

antelope-data-1024

Repeats: 0
Total number of images: ~6
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 PixArtSigmaPipeline, PixArtSigmaControlNetPipeline
# if you're not in the SimpleTuner environment, this import will fail.
from helpers.models.pixart.controlnet import PixArtSigmaControlNetAdapterModel

# Load base model
base_model_id = "terminusresearch/pixart-900m-1024-ft-v0.6"
controlnet_id = "bghira/pixart-controlnet-lora-test"

# Load ControlNet adapter
controlnet = PixArtSigmaControlNetAdapterModel.from_pretrained(
    f"{controlnet_id}/controlnet"
)

# Create pipeline
pipeline = PixArtSigmaControlNetPipeline.from_pretrained(
    base_model_id,
    controlnet=controlnet,
    torch_dtype=torch.bfloat16
)
pipeline.to('cuda' if torch.cuda.is_available() else 'cpu')

# Load your control image
from PIL import Image
control_image = Image.open("path/to/control/image.png")

# Generate
prompt = "A photo-realistic image of a cat"
image = pipeline(
    prompt=prompt,
    image=control_image,
    num_inference_steps=16,
    guidance_scale=4.0,
    generator=torch.Generator(device='cuda').manual_seed(42),
    controlnet_conditioning_scale=1.0,
).images[0]

image.save("output.png")