lora-training

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

The main validation prompt used during training was:

 a person's portrait.

Validation settings

CFG: 3.5
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.

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

Training settings

Training epochs: 90
Training steps: 900
Learning rate: 1e-05
Effective batch size: 8
- Micro-batch size: 2
- Gradient accumulation steps: 4
- Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: AdamW, stochastic bf16
Precision: Pure BF16
Xformers: Enabled
LoRA Rank: 16
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

Flux_Moody

Repeats: 0
Total number of images: 80
Total number of aspect buckets: 1
Resolution: 1 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 = 'diegochavez/lora-training'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = " a person's portrait."


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=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=1024,
    height=1024,
    guidance_scale=3.5,
).images[0]
image.save("output.png", format="PNG")