Stellaa-Flux-Lora-52img-v1

This is a standard PEFT LoRA derived from black-forest-labs/FLUX.1-dev.

The main validation prompt used during training was:

in the style of Stellaa

Validation settings

• CFG: 3.0
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• Seed: 42
• Resolutions: 1024x1024,832x1216

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

You can find some example images in the following gallery:

Prompt

unconditional (blank prompt)

Negative Prompt

blurry, cropped, ugly

Prompt

unconditional (blank prompt)

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of Stellaa

Negative Prompt

blurry, cropped, ugly

Prompt

in the style of Stellaa

Negative Prompt

blurry, cropped, ugly

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

Training settings

• Training epochs: 110
• Training steps: 5200
• Learning rate: 0.0001
• Effective batch size: 2
  • Micro-batch size: 2
  • Gradient accumulation steps: 1
  • Number of GPUs: 1
• Prediction type: flow-matching
• Rescaled betas zero SNR: False
• Optimizer: adamw_bf16
• Precision: bf16
• Quantised: No
• Xformers: Not used
• LoRA Rank: 16
• LoRA Alpha: None
• LoRA Dropout: 0.1
• LoRA initialisation style: default

Datasets

Stellaa

• Repeats: 0
• Total number of images: 50
• Total number of aspect buckets: 1
• Resolution: 1.048576 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

Stellaa_arb

• Repeats: 0
• Total number of images: 43
• Total number of aspect buckets: 2
• Resolution: 1.0 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'SHotoor/Stellaa-Flux-Lora-52img-v1'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "in the style of Stellaa"

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=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(1641421826),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")