README.md

metadata

license: other
base_model: black-forest-labs/FLUX.1-dev
tags:
  - flux
  - flux-diffusers
  - text-to-image
  - diffusers
  - simpletuner
  - safe-for-work
  - 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: a close up photo of an orange cat with airplane ears
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png
  - text: >-
      a photo of a black cat with airplane ears sitting in the cockpit of a
      boeing 747 airplane with the twin towers in the background on September
      11th, 2001
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_2_0.png
  - text: a photo of a fluffy white cat with airplane ears
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_3_0.png

airplaneears-flux

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

The main validation prompt used during training was:

a photo of a fluffy white cat with airplane ears

Validation settings

• CFG: 3.0
• CFG Rescale: 0.0
• Steps: 20
• Sampler: None
• Seed: 42
• Resolution: 1024x1024

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

a close up photo of an orange cat with airplane ears

Negative Prompt

blurry, cropped, ugly

Prompt

a photo of a black cat with airplane ears sitting in the cockpit of a boeing 747 airplane with the twin towers in the background on September 11th, 2001

Negative Prompt

blurry, cropped, ugly

Prompt

a photo of a fluffy white cat with airplane ears

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: 10
• Training steps: 5200
• Learning rate: 2e-05
• 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: optimi-lion
• Precision: Pure BF16
• Quantised: Yes: int8-quanto
• Xformers: Not used
• LoRA Rank: 16
• LoRA Alpha: None
• LoRA Dropout: 0.1
• LoRA initialisation style: default

Datasets

airplaneears-512

• Repeats: 5
• Total number of images: 39
• Total number of aspect buckets: 6
• Resolution: 0.262144 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

airplaneears-768

• Repeats: 5
• Total number of images: 35
• Total number of aspect buckets: 9
• Resolution: 0.589824 megapixels
• Cropped: False
• Crop style: None
• Crop aspect: None

airplaneears-512-crop

• Repeats: 5
• Total number of images: 35
• Total number of aspect buckets: 1
• Resolution: 0.262144 megapixels
• Cropped: True
• Crop style: random
• Crop aspect: square

airplaneears-768-crop

• Repeats: 5
• Total number of images: 39
• Total number of aspect buckets: 1
• Resolution: 0.589824 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 = 'markury/airplaneears-flux'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "a photo of a fluffy white cat with airplane ears"

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