flux-training / README.md
Hius's picture
Model card auto-generated by SimpleTuner
88fd361 verified
metadata
license: creativeml-openrail-m
base_model: black-forest-labs/FLUX.1-dev
tags:
  - stable-diffusion
  - stable-diffusion-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - lora
  - template:sd-lora
inference: true
widget:
  - text: unconditional (blank prompt)
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_0_0.png
  - text: >-
      Porcelain style, this is a blue and white ceramic plate depicting a fox
      and its cubs strolling in the forest, with a white background
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png

flux-training

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

The main validation prompt used during training was:

Porcelain style, this is a blue and white ceramic plate depicting a fox and its cubs strolling in the forest, with a white background

Validation settings

  • CFG: 7.5
  • 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:

Prompt
unconditional (blank prompt)
Negative Prompt
blurry, cropped, ugly
Prompt
Porcelain style, this is a blue and white ceramic plate depicting a fox and its cubs strolling in the forest, with a white background
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: 22
  • Training steps: 200
  • Learning rate: 1e-05
  • Effective batch size: 16
    • Micro-batch size: 4
    • 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: loftq

Datasets

hius-flux

  • Repeats: 0
  • Total number of images: 144
  • Total number of aspect buckets: 1
  • Resolution: 512 px
  • 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 = 'flux-training'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "Porcelain style, this is a blue and white ceramic plate depicting a fox and its cubs strolling in the forest, with a white background"


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")