FLUX.1 dev SimpleTuner Test

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

The main validation prompt used during training was:

a photo of man

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.

You can find some example images in the following gallery:

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

Training settings

Training epochs: 30
Training steps: 150
Learning rate: 8e-07
Effective batch size: 64
- Micro-batch size: 16
- Gradient accumulation steps: 4
- Number of GPUs: 1
Prediction type: epsilon
Rescaled betas zero SNR: False
Optimizer: AdamW, stochastic bf16
Precision: Pure BF16
Xformers: Not used
LoRA Rank: 16
LoRA Alpha: 16
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

AndroFlow

Repeats: 0
Total number of images: 320
Total number of aspect buckets: 1
Resolution: 1 megapixels
Cropped: True
Crop style: random
Crop aspect: square

Inference

import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'AndroFlow-FLUX-SimpleTuner-1'
pipeline = DiffusionPipeline.from_pretrained(model_id)\pipeline.load_adapter(adapter_id)

prompt = "a photo of man"
negative_prompt = ""

pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu')
image = pipeline(
    prompt=prompt,
    negative_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=1152,
    height=768,
    guidance_scale=3.5,
    guidance_rescale=0.0,
).images[0]
image.save("output.png", format="PNG")