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: >-
      es_style, two figures embraced, one male: red cap, one female: black
      headdress, standing, hands clasped close, greenish background, earthy
      tones, muted colors, asymmetrical balance, shadowy harmony, textured
      brushwork, high contrast, layered application, melancholic, signature
      bottom-right
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: >-
      es_style, 2 figures (woman: brown dress, child: orange clothing), intimate
      embrace, minimal background, muted tones, textured brushwork, loosely
      defined, asymmetrical balance, melancholic, signature bottom-left
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: >-
      es_style, single figure (man: brown suit, red tie), no background detail,
      muted tones, asymmetrical balance, textured brushwork, sharp contours,
      rhythmic patterns, melancholic, signature bottom-left
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png
  - text: >-
      es_style, single female figure, red headband, simple draped fabric,
      looking downward, indoor setting, white background, light beige hues, dark
      lines, asymmetrical balance, muted tones, sharp contours, dynamic energy,
      serene, signature bottom-right
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_4_0.png
  - text: >-
      mp_style, Street scene, 50 figures (many women: colorful dresses, many
      men: suits), 23 umbrellas (orange, red, yellow, green), bridge, buildings
      background, water, boats, Italian flag, steps, lamps, crowd ascending
      descending bridge, signature bottom-left
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_5_0.png

lora-Egon-Schiele-Flux

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

The main validation prompt used during training was:

mp_style, Street scene, 50 figures (many women: colorful dresses, many men: suits), 23 umbrellas (orange, red, yellow, green), bridge, buildings background, water, boats, Italian flag, steps, lamps, crowd ascending descending bridge, signature bottom-left

Validation settings

CFG: 7.5
CFG Rescale: 0.0
Steps: 20
Sampler: None
Seed: 42
Resolution: 512

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
es_style, two figures embraced, one male: red cap, one female: black headdress, standing, hands clasped close, greenish background, earthy tones, muted colors, asymmetrical balance, shadowy harmony, textured brushwork, high contrast, layered application, melancholic, signature bottom-right

Negative Prompt
blurry, cropped, ugly

Prompt
es_style, 2 figures (woman: brown dress, child: orange clothing), intimate embrace, minimal background, muted tones, textured brushwork, loosely defined, asymmetrical balance, melancholic, signature bottom-left

Negative Prompt
blurry, cropped, ugly

Prompt
es_style, single figure (man: brown suit, red tie), no background detail, muted tones, asymmetrical balance, textured brushwork, sharp contours, rhythmic patterns, melancholic, signature bottom-left

Negative Prompt
blurry, cropped, ugly

Prompt
es_style, single female figure, red headband, simple draped fabric, looking downward, indoor setting, white background, light beige hues, dark lines, asymmetrical balance, muted tones, sharp contours, dynamic energy, serene, signature bottom-right

Negative Prompt
blurry, cropped, ugly

Prompt
mp_style, Street scene, 50 figures (many women: colorful dresses, many men: suits), 23 umbrellas (orange, red, yellow, green), bridge, buildings background, water, boats, Italian flag, steps, lamps, crowd ascending descending bridge, signature bottom-left

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: 3
Training steps: 440
Learning rate: 0.0004
Effective batch size: 1
- Micro-batch size: 1
- Gradient accumulation steps: 1
- Number of GPUs: 1
Prediction type: flow-matching
Rescaled betas zero SNR: False
Optimizer: AdamW, stochastic bf16
Precision: Pure BF16
Quantised: No
Xformers: Not used
LoRA Rank: 64
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

EgonSchiele

Repeats: 0
Total number of images: 122
Total number of aspect buckets: 1
Resolution: 1024 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 = 'davidrd123/lora-Egon-Schiele-Flux'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "mp_style, Street scene, 50 figures (many women: colorful dresses, many men: suits), 23 umbrellas (orange, red, yellow, green), bridge, buildings background, water, boats, Italian flag, steps, lamps, crowd ascending descending bridge, signature bottom-left"


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=512,
    height=512,
    guidance_scale=7.5,
).images[0]
image.save("output.png", format="PNG")