Training epochs: 1999
Training steps: 2000
Learning rate: 1e-06
Effective batch size: 8
- Micro-batch size: 4
- Gradient accumulation steps: 2
- Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: AdamW, stochastic bf16
Precision: Pure BF16
Xformers: Not used
LoRA Rank: 4
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

Hermes-handbag

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

Inference

python

import torch
from diffusers import DiffusionPipeline

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

prompt = "xwe hermes handbag, photo of woman lower part posing on city street clad in white holding a xwe hermes handbag"


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=7.5,
).images[0]
image.save("output.png", format="PNG")