README.md

---
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: >-
    In the style of a b3nbr4nd painting, A steaming bowl of ramen with
    chopsticks resting on the edge, against a background of concentric orange
    and blue circles. The noodles are detailed in a geometric pattern and the
    steam creates a rhythmic design.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_1_0.png
- text: >-
    In the style of a b3nbr4nd painting, A vintage record player with vinyl
    spinning, set on a yellow table. The background features an alternating
    chevron pattern in purple and green. The turntable's mechanical parts are
    rendered in precise geometric shapes.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_2_0.png
- text: >-
    In the style of a b3nbr4nd painting, A sleeping cat curled up in a modernist
    chair, with a background of interlocking hexagons in red and blue. The cat's
    fur is stylized into rhythmic curves, matching the geometric environment.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_3_0.png
- text: >-
    In the style of a b3nbr4nd painting, A classic motorcycle viewed from the
    side, against a backdrop of radiating diamond patterns in teal and gold. The
    chrome parts reflect abstract shapes, and the wheels create circular motifs
    in the composition.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_4_0.png
- text: >-
    In the style of a b3nbr4nd painting, Portrait of a woman with silver hair
    wearing dotted blue glasses and a white lace collar, against a swirling
    background of green and yellow patterns. The background features geometric
    circles and zigzag designs.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_5_0.png
- text: >-
    In the style of a b3nbr4nd painting, A storefront sign for 'Golden Palace
    Noodles' in both English and Chinese characters, mounted on a tall pole
    against a geometric cityscape with blue and tan buildings. A small arrow
    points to available parking.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_6_0.png
- text: >-
    In the style of a b3nbr4nd painting, Dark purple figs sliced in half on a
    terra cotta plate, revealing their seeded interiors. The background features
    a repeating pattern of blue and yellow squares, with wavy lines creating a
    dynamic lower section.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_7_0.png
- text: >-
    In the style of a b3nbr4nd painting, Two young people wearing matching navy
    shirts and light gray face masks, posed against a warm yellow background.
    Their curly hair and gentle head tilts create a symmetrical composition.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_8_0.png
- text: >-
    In the style of a b3nbr4nd painting, A hamster wearing tiny glasses and a
    bowtie sitting at a miniature desk with a tiny laptop, against a background
    of spiral patterns in teal and orange. Office supplies scaled to
    hamster-size are arranged neatly on the desk.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_9_0.png
- text: >-
    In the style of a b3nbr4nd painting, A bearded man in a plaid shirt and
    denim apron carefully sanding a mid-century modern chair, surrounded by
    woodworking tools. The background features overlapping triangles in rust and
    navy blue colors, with sawdust creating delicate patterns in the air.
  parameters:
    negative_prompt: blurry, cropped, ugly
  output:
    url: ./assets/image_10_0.png
- text: >-
    In the style of a b3nbr4nd painting, windows, hanging lights, cube shapes,
    night sky, interior, glass walls, cityscape view, reflections, indoor
    lighting, architectural design, ceiling grid, geometric shapes, open space,
    floor reflection, frame structures, exterior environment, horizon, enclosed
    glass room, symmetrical arrangement.
  output:
    url: images/example_1o217307s.png
- text: >-
    In the style of a b3nbr4nd painting, A light-skinned, blonde-haired
    character with blue-green eyes is partially hidden behind a dark brown
    wooden easel, holding a thin paintbrush in their right hand. They are
    wearing a dark grey long-sleeved shirt and are positioned in a room with a
    window showing greenery outside. Sunlight appears to be coming through the
    window, casting a warm light on the scenes
  output:
    url: images/example_ucr8z54gk.png
- text: >-
    In the style of a b3nbr4nd painting, snake, black snakes, desert, cacti,
    cactus, prickly pear cactus, yucca plant, orange eye, mountains, purple
    mountains, blue sky, green cactus, yellow desert, close-up view, coiled
    snake, landscape, arid environment, vegetation, plant, side view, foreground
    snake, background mountains
  output:
    url: images/example_dzflrmjnh.png
- text: >-
    In the style of a b3nbr4nd painting, elephant, blue elephant, pink earz,
    yellow stars on ears, tusks, LV logo on forehead, standing in water, night
    sky, stars, hills in background, orange sun, grassy hills, river, centered
    composition, foreground elephant, background hills, detailed ears, yellow
    tusks
  output:
    url: images/example_qcn3jzw0k.png
- text: >-
    In the style of a b3nbr4nd painting, Lone cowboy with a neon-accented black
    hat, glowing blue trench coat, high-tech revolver, walking through a desert
    with holographic cacti, distant monolithic structures, sunset merging with
    neon city lights.
  output:
    url: images/example_gdmyxo62r.png
- text: >-
    In the style of a b3nbr4nd painting, Grand hallway lined with glowing
    arches, checkerboard floors reflecting celestial patterns, tall crystalline
    windows revealing a surreal pink and blue landscape beyond, sense of
    infinite depth.
  output:
    url: images/example_z0ltdvvt2.png
- text: >-
    In the style of a b3nbr4nd painting, Enormous coiled serpent with shimmering
    obsidian scales, golden eyes, desert dunes stretching infinitely behind,
    ancient ruins partially buried in sand, cryptic glowing runes along its
    spine, divine protector vibe.
  output:
    url: images/example_rr77xfv4s.png
- text: >-
    In the style of a b3nbr4nd painting, Futuristic city with towering glass
    spires, floating walkways, cascading waterfalls from sky bridges, deep
    twilight hues, citizens in glowing garments, neon signage in an unknown
    language, misty ethereal lighting.
  output:
    url: images/example_zspcepsdq.png
- text: >-
    In the style of a b3nbr4nd painting, Hooded woman with three eyes, one on
    forehead glowing white, intricate tattoos on hands, sitting before a pool of
    shifting liquid light, ancient walls covered in carved symbols, deep,
    resonant mysticism.
  output:
    url: images/example_f3lzi6acu.png
- text: >-
    In the style of a b3nbr4nd painting, Grand temple with floating stained
    glass windows that shift and realign, monks kneeling in meditation, luminous
    orbs orbiting them, ceiling expanding into a night sky filled with
    constellations forming living creatures.
  output:
    url: images/example_j3hxhqdp3.png
- text: >-
    In the style of a b3nbr4nd painting, Arching bridge leading to a glowing
    circular portal, clouds parting to reveal an upside-down city in the sky,
    robed traveler stepping forward cautiously, vibrant auroras shimmering at
    the edges.
  output:
    url: images/example_p6j5bwso5.png
- text: >-
    In the style of a b3nbr4nd painting, Towering domed structure suspended
    among the clouds, enormous telescopes extending outward, luminous pathways
    leading to observation decks, a planetary system reflected in the massive
    glass walls, scholars watching celestial phenomena.
  output:
    url: images/example_f0y7q6w9w.png
- text: >-
    In the style of a b3nbr4nd painting, Towering bookshelves stretching into
    the horizon, glowing tomes levitating mid-air, staircases spiraling into
    unknown dimensions, a robed figure holding an open book with pages
    unraveling into stardust.
  output:
    url: images/example_dflnkpmzp.png
- text: >-
    In the style of a b3nbr4nd painting, Lone traveler in tattered robes riding
    a skeletal horse, dust storm swirling around, faint glows of lost souls
    flickering in the dunes, cracked earth revealing an ancient, forgotten road.
  output:
    url: images/example_0fe2ayczq.png
- text: >-
    In the style of a b3nbr4nd painting, Enormous clockwork mechanism suspended
    in a dark void, gears turning with golden precision, celestial bodies
    orbiting in synchronized harmony, lone figure adjusting levers, determining
    the fate of time itself.
  output:
    url: images/example_lb95251sm.png
- text: >-
    In the style of a b3nbr4nd painting, A vast hall of glowing manuscripts,
    suspended in midair, pages turning on their own, ink shifting and rewriting
    itself, golden runes pulsing with ancient intent, a hooded figure walking
    the aisles, reading a text that changes as they do.
  output:
    url: images/example_lkzcxa76f.png

---

# Ben-Brand-LoRA

This is a standard PEFT LoRA derived from [black-forest-labs/FLUX.1-dev](https://huggingface.co./black-forest-labs/FLUX.1-dev).


No validation prompt was used during training.

None



## Validation settings
- CFG: `3.0`
- CFG Rescale: `0.0`
- Steps: `20`
- Sampler: `FlowMatchEulerDiscreteScheduler`
- Seed: `42`
- Resolution: `1024x1024`
- Skip-layer guidance: 

Note: The validation settings are not necessarily the same as the [training settings](#training-settings).

You can find some example images in the following gallery:


<Gallery />

The text encoder **was not** trained.
You may reuse the base model text encoder for inference.


## Training settings

- Training epochs: 1
- Training steps: 3000
- Learning rate: 0.0001
  - Learning rate schedule: polynomial
  - Warmup steps: 100
- Max grad norm: 0.1
- Effective batch size: 6
  - Micro-batch size: 2
  - Gradient accumulation steps: 3
  - Number of GPUs: 1
- Gradient checkpointing: True
- Prediction type: flow-matching (extra parameters=['shift=3', 'flux_guidance_mode=constant', 'flux_guidance_value=1.0', 'flow_matching_loss=compatible', 'flux_lora_target=all'])
- Optimizer: adamw_bf16
- Trainable parameter precision: Pure BF16
- Caption dropout probability: 10.0%


- LoRA Rank: 64
- LoRA Alpha: None
- LoRA Dropout: 0.1
- LoRA initialisation style: default
    

## Datasets

### ben-brand-256
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 6
- Resolution: 0.065536 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-256
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 0.065536 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### ben-brand-512
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 4
- Resolution: 0.262144 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-512
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 0.262144 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### ben-brand-768
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 3
- Resolution: 0.589824 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-768
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 0.589824 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### ben-brand-1024
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 2
- Resolution: 1.048576 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-1024
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 1.048576 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No
### ben-brand-1440
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 8
- Resolution: 2.0736 megapixels
- Cropped: False
- Crop style: None
- Crop aspect: None
- Used for regularisation data: No
### ben-brand-crop-1440
- Repeats: 10
- Total number of images: 98
- Total number of aspect buckets: 1
- Resolution: 2.0736 megapixels
- Cropped: True
- Crop style: center
- Crop aspect: square
- Used for regularisation data: No


## Inference


```python
import torch
from diffusers import DiffusionPipeline

model_id = 'black-forest-labs/FLUX.1-dev'
adapter_id = 'davidrd123/Ben-Brand-LoRA'
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
pipeline.load_lora_weights(adapter_id)

prompt = "An astronaut is riding a horse through the jungles of Thailand."


## Optional: quantise the model to save on vram.
## Note: The model was quantised during training, and so it is recommended to do the same during inference time.
from optimum.quanto import quantize, freeze, qint8
quantize(pipeline.transformer, weights=qint8)
freeze(pipeline.transformer)
    
pipeline.to('cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu') # the pipeline is already in its target precision level
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(42),
    width=1024,
    height=1024,
    guidance_scale=3.0,
).images[0]
image.save("output.png", format="PNG")
```