simpletuner-lora

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

The main validation prompt used during training was:

Enhance the image to feature the individual in a well-lit interior setting, utilizing soft, diffused lighting that highlights the texture and elegance of the traditional brown agbada. Position the individual with an upright posture, ensuring the red cap is prominently displayed as a focal point. Transform the background to showcase a vivid, picturesque snowy landscape visible through a large, clean window, ensuring the snow is pristine and the scene is well-balanced to convey a sense of serenity and warmth inside. Maintain the overall composition that combines the richness of traditional attire with the tranquil beauty of the winter scenery.

Validation settings

• CFG: 3.0
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• 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: 1999
• Training steps: 0
• Learning rate: 0.0001
• Effective batch size: 4
  • Micro-batch size: 1
  • Gradient accumulation steps: 1
  • Number of GPUs: 4
• 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

namo

• Repeats: 0
• Total number of images: ~8
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: True
• Crop style: center
• Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'zaddyzaddy/simpletuner-lora'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "Enhance the image to feature the individual in a well-lit interior setting, utilizing soft, diffused lighting that highlights the texture and elegance of the traditional brown agbada. Position the individual with an upright posture, ensuring the red cap is prominently displayed as a focal point. Transform the background to showcase a vivid, picturesque snowy landscape visible through a large, clean window, ensuring the snow is pristine and the scene is well-balanced to convey a sense of serenity and warmth inside. Maintain the overall composition that combines the richness of traditional attire with the tranquil beauty of the winter scenery."

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")