Hugging Face's logo

gattaplayer
/
besch-style-st-sd35l-lora-6e-6-bs3-v02

Text-to-Image
Diffusers
sd3
sd3-diffusers
simpletuner
Not-For-All-Audiences
lora
template:sd-lora
standard
Model card Files Community
Edit model card

besch-style-st-sd35l-lora-6e-6-bs3-v02

This is a standard PEFT LoRA derived from stabilityai/stable-diffusion-3.5-large.

No validation prompt was used during training.

None

Validation settings

  • CFG: 4.5
  • CFG Rescale: 0.0
  • Steps: 20
  • Sampler: None
  • Seed: 4118992873
  • Resolution: 832x1216

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
the face of a girl in the foreground with windswept red hair, green eyes full of determination, while a soft light highlights her
Negative Prompt
blurry, cropped, ugly
Prompt
a beautiful woman with flowing hair adorned with flowers and intricate patterns, her expression is confident and mysterious as she holds her hand near her face, she wears an ornate outfit with floral designs, her skin and features are bathed in soft pink tones, the background is filled with decorative swirls and patterns that enhance the elegant and sensual atmosphere, the overall composition is delicate and detailed with a romantic and alluring vibe
Negative Prompt
blurry, cropped, ugly
Prompt
a seductive vampire woman with long flowing dark hair and pale skin, wearing a revealing outfit, she stands in a mystical pose under a crescent moon, her hands raised gracefully as a bat flies above her, her expression is serene and mysterious, the background features dark clouds and a glowing moon halo, creating an ethereal and supernatural atmosphere with soft lighting and shadows, the overall vibe is dark, alluring, and filled with gothic fantasy elements
Negative Prompt
blurry, cropped, ugly
Prompt
a woman with long flowing hair in a seductive pose, her body highlighted by soft blue and pink neon lighting, she glances over her shoulder with an intense and mysterious expression, the background features abstract patterns with a retro-futuristic style, combining halftone dots and sharp angular lines, the lighting creates dramatic shadows, emphasizing her curves and giving the scene a vibrant yet moody atmosphere with a mix of sensuality and artistic flair
Negative Prompt
blurry, cropped, ugly
Prompt
a stylish young woman with short, white-blonde hair, wearing a sleek, light-colored outfit, she stands against a dark background illuminated by vibrant, glowing yellow flowers, her eyes are sharp and glowing with a soft light, petals and embers float around her, giving the scene an ethereal and fiery atmosphere, the contrast between the dark background and the bright flowers creates a striking visual, combining beauty and intensity with a modern and artistic touch
Negative Prompt
blurry, cropped, ugly
Prompt
a dynamic and intense scene featuring a stylized woman with vibrant, neon-lit colors, her body twists in an expressive pose with her arms raised above her head, she has bold makeup, including large heart-shaped blush marks on her cheeks, and her hair flows wildly, illuminated with streaks of pink, blue, and green, she wears a dark, form-fitting outfit with torn, textured patterns that glow under the neon lights, the background is a chaotic mix of abstract splashes and geometric graffiti-like designs, with bright neon greens and pinks contrasting against the dark, midnight-blue backdrop, the overall vibe is energetic and rebellious, with a futuristic, cyberpunk aesthetic and a sense of movement and electricity in the air
Negative Prompt
blurry, cropped, ugly
Prompt
profile of a dark-skinned woman with long blonde hair and green-yellow eyes, set against a background of large, vibrant leaves in shades of green, yellow, and red, the leaves dominate the foreground, creating a vivid contrast with the woman’s calm and focused expression, as if she is deep in thought, the lighting highlights her face and hair subtly, while the foliage around her adds a sense of motion and energy, the background fades into deeper greens and yellows
Negative Prompt
blurry, cropped, ugly
Prompt
a woman with long red hair is shown in a curled-up pose, her face tilted toward her knees, gazing intensely at the camera with a look that combines vulnerability and curiosity, her lips are slightly parted, adding a sense of intrigue, while her green eyes, half-shaded by her bangs, convey a mixture of thoughtfulness and quiet intensity, she wears a bright orange headband that contrasts vividly with the green of her outfit and the background, the outfit is made of olive-green lace, with intricate embroidery that stands out against her fair skin, her left arm is bent and rests on her leg, adorned with an ornate gold bracelet featuring white and black details, the background is a muted teal-green, which enhances the bold colors of the image, creating an elegant contrast between warm and cool tones, the overall atmosphere is sophisticated, with a mix of sensuality, mystery, and strength conveyed through her expressive gaze and compact pose
Negative Prompt
blurry, cropped, ugly
Prompt
a blonde woman, gazing with a confident and relaxed expression, she is wearing a voluminous orange-red fur coat that immediately catches the eye, the soft, fluffy texture contrasts with the gray stone architecture behind her, underneath the coat, a light gray satin sleeve elegantly peeks out, her hands are crossed, adorned with thin, modern rings, the background reveals a quiet city street with historical buildings in neutral tones
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: 8770
  • Learning rate: 6e-06
  • Max grad norm: 0.01
  • Effective batch size: 3
    • Micro-batch size: 3
    • Gradient accumulation steps: 1
    • Number of GPUs: 1
  • Prediction type: flow-matching (extra parameters=['shift=3'])
  • Optimizer: adamw_bf16
  • Trainable parameter precision: Pure BF16
  • Quantised base model: No
  • Xformers: Not used
  • LoRA Rank: 64
  • LoRA Alpha: 64.0
  • LoRA Dropout: 0.1
  • LoRA initialisation style: default

Datasets

BESCH-CROP-SD35L-V02-512

  • Repeats: 1
  • Total number of images: 104
  • Total number of aspect buckets: 1
  • Resolution: 0.262144 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-CROP-SD35L-V02-768

  • Repeats: 1
  • Total number of images: 104
  • Total number of aspect buckets: 1
  • Resolution: 0.589824 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-CROP-SD35L-V02-1024

  • Repeats: 1
  • Total number of images: 104
  • Total number of aspect buckets: 3
  • Resolution: 1.048576 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-CROP-SD35L-V02-1280

  • Repeats: 1
  • Total number of images: 104
  • Total number of aspect buckets: 3
  • Resolution: 1.6384 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-MIX-SD35L-V02-512

  • Repeats: 1
  • Total number of images: 215
  • Total number of aspect buckets: 3
  • Resolution: 0.262144 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-MIX-SD35L-V02-768

  • Repeats: 1
  • Total number of images: 215
  • Total number of aspect buckets: 2
  • Resolution: 0.589824 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-MIX-SD35L-V02-1024

  • Repeats: 1
  • Total number of images: 214
  • Total number of aspect buckets: 3
  • Resolution: 1.048576 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-MIX-SD35L-V02-1280

  • Repeats: 1
  • Total number of images: 212
  • Total number of aspect buckets: 1
  • Resolution: 1.6384 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

Inference 

import torch
from diffusers import DiffusionPipeline

model_id = 'stabilityai/stable-diffusion-3.5-large'
adapter_id = 'gattaplayer/besch-style-st-sd35l-lora-6e-6-bs3-v02'
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."
negative_prompt = 'blurry, cropped, ugly'

## Optional: quantise the model to save on vram.
## Note: The model was not quantised during training, so it is not necessary to quantise it 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,
    negative_prompt=negative_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=832,
    height=1216,
    guidance_scale=4.5,
).images[0]
image.save("output.png", format="PNG")
Downloads last month
94
Inference API
Text-to-Image
Examples

Model tree for gattaplayer/besch-style-st-sd35l-lora-6e-6-bs3-v02

Base model

stabilityai/stable-diffusion-3.5-large
Adapter
(131)
this model