metadata

license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - not-for-all-audiences
  - lora
  - template:sd-lora
  - standard
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: >-
      casual profile headshot photo of TOK woman for instagram. hasselblad
      photography.
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png

simpletuner-lora

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

The main validation prompt used during training was:

casual profile headshot photo of TOK woman for instagram. hasselblad photography.

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: euler
Seed: 42
Resolution: 576x1024

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
casual profile headshot photo of TOK woman for instagram. hasselblad photography.

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: 14
Training steps: 1250
Learning rate: 0.0005
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: Pure BF16
Quantised: No
Xformers: Not used
LoRA Rank: 16
LoRA Alpha: 16.0
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

rita-512

Repeats: 10
Total number of images: 16
Total number of aspect buckets: 1
Resolution: 0.262144 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 = 'naumnaum/simpletuner-lora'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "casual profile headshot photo of TOK woman for instagram. hasselblad photography."

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=576,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")