simpletuner-lora

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

The main validation prompt used during training was:

An illustration of a serene landscape at night, moonlit mountain scene, tall pine trees on a small island, snow-capped mountains in the background, still lake reflecting trees and full moon, cloud-speckled sky dotted with stars, soft ambient lighting, primary color tones of blue and white, ambient and tranquil atmosphere, high resolution, extremely detailed.

Validation settings

CFG: 3.0
CFG Rescale: 0.0
Steps: 20
Sampler: None
Seed: 42
Resolution: 1344x768

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
night landscape, full moon, starry sky, mountain silhouette, glowing moon, fireflies, illuminated grass, forest trees, blue tone, serene atmosphere, dreamy scene, outdoor wilderness, natural beauty, twilight, nocturnal environment, magical ambiance, night photography, moonlit field, peaceful setting, lush greenery

Negative Prompt
blurry, cropped, ugly

Prompt
Dense forest, ancient tree, wooden bridge, moss-covered, flowing stream, mystical atmosphere, high resolution, balanced composition, green foliage, misty background, realistic photography, soft natural light, lush greenery, nature scenery, serene, tranquil mood, detailed texture, vibrant greens, forest pathway, overgrown.

Negative Prompt
blurry, cropped, ugly

Prompt
cabin in the woods, misty forest, realistic photography, centered composition, high resolution, dark color palette, soft evening light, front view, wooden texture, eerie atmosphere, warm interior light, serene setting, reflective water surface, overcast sky, rustic house, forested landscape, dim lighting, reflective puddles, wet ground, cozy yet mysterious ambiance

Negative Prompt
blurry, cropped, ugly

Prompt
An illustration of a serene landscape at night, moonlit mountain scene, tall pine trees on a small island, snow-capped mountains in the background, still lake reflecting trees and full moon, cloud-speckled sky dotted with stars, soft ambient lighting, primary color tones of blue and white, ambient and tranquil atmosphere, high resolution, extremely detailed.

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: 9
Training steps: 10000
Learning rate: 0.0001
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: bf16
Quantised: Yes: int8-quanto
Xformers: Not used
LoRA Rank: 16
LoRA Alpha: 16.0
LoRA Dropout: 0.1
LoRA initialisation style: default

Datasets

pseudo-natural-booru-flux

Repeats: 0
Total number of images: 1089
Total number of aspect buckets: 1
Resolution: 1.048576 megapixels
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 = 'datnt114/simpletuner-lora'
pipeline = DiffusionPipeline.from_pretrained(model_id)
pipeline.load_lora_weights(adapter_id)

prompt = "An illustration of a serene landscape at night, moonlit mountain scene, tall pine trees on a small island, snow-capped mountains in the background, still lake reflecting trees and full moon, cloud-speckled sky dotted with stars, soft ambient lighting, primary color tones of blue and white, ambient and tranquil atmosphere, high resolution, extremely detailed."

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=1344,
    height=768,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")