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: photo of a modern architectural interior event space at dusk
    parameters:
      negative_prompt: blurry, cropped, ugly
    output:
      url: ./assets/image_1_0.png

simpletuner-lora-spindrift

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

The main validation prompt used during training was:

photo of a modern architectural interior event space at dusk

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 25
Sampler: None
Seed: 42
Resolution: 1216x832

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
photo of a modern architectural interior event space at dusk

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: 0
Training steps: 1000
Learning rate: 1e-05
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_bf16
Precision: Pure BF16
Quantised: Yes: int8-quanto
Xformers: Not used
LoRA Rank: 64
LoRA Alpha: None
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

spindrift-dataset-512

Repeats: 25
Total number of images: 29
Total number of aspect buckets: 6
Resolution: 0.262144 megapixels
Cropped: False
Crop style: None
Crop aspect: None

spindrift-dataset-1024

Repeats: 25
Total number of images: 32
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
Cropped: False
Crop style: None
Crop aspect: None

spindrift-dataset-512-crop

Repeats: 25
Total number of images: 32
Total number of aspect buckets: 1
Resolution: 0.262144 megapixels
Cropped: True
Crop style: random
Crop aspect: square

spindrift-dataset-1024-crop

Repeats: 25
Total number of images: 32
Total number of aspect buckets: 1
Resolution: 1.048576 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 = 'spawn99/simpletuner-lora-spindrift'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "photo of a modern architectural interior event space at dusk"

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=25,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1641421826),
    width=1216,
    height=832,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")