Hugging Face's logo

gattaplayer
/
besch-style-st-sd35m-lokr-25e-6-bs6-v04

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

besch-style-st-sd35m-lokr-25e-6-bs6-v04

This is a LyCORIS adapter derived from stabilityai/stable-diffusion-3.5-medium.

No validation prompt was used during training.

None

Validation settings

  • CFG: 4.0
  • CFG Rescale: 0.0
  • Steps: 30
  • Sampler: FlowMatchEulerDiscreteScheduler
  • Seed: 1121925699670477
  • Resolution: 832x1216
  • Skip-layer guidance: skip_guidance_layers=[7, 8, 9],

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 of a young woman 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 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 mesmerizing woman with flowing orange-blonde hair cascading down her back her piercing green eyes framed by vibrant blue eyelashes gaze directly at the viewer contrasting beautifully with her bold orange eyebrows her pink lips add a soft yet striking touch she wears a flowing pink cape that glimmers with delicate sparkles catching the light her pose is elegant with her back turned to the camera yet her expression exudes confidence and mystery as she looks over her shoulder
Negative Prompt
blurry, cropped, ugly
Prompt
a seductive vampire , her pale porcelain skin gleams with ethereal light while shadows dance across her skin her deep black hair flows dramatically with hints of blue and purple highlights her crimson lips part in a serene expression, her minimal dark outfit enhance her elegance surrounded by swirling pink and teal clouds in a moody nocturnal sky
Negative Prompt
blurry, cropped, ugly
Prompt
a jungle queen with piercing green eyes her long blonde hair is adorned with flowers and feathers partially catching the light her face is dramatically lit with sharp contrasts one side glowing warmly while the other is cast in soft shadow creating depth and mystery the light highlights her vibrant green eyes and glossed lips while the shadow accentuates her cheekbones and jawline the jungle backdrop intensifies the luminous and moody atmosphere surrounding her
Negative Prompt
blurry, cropped, ugly
Prompt
a confident young queen with flowing blonde hair and striking blue eyes her gaze is bold and captivating her face illuminated by soft yet dynamic lighting emphasizing the gloss on her lips and the glow of her complexion she wears a hood adorned with playful designs a bold pink heart stands out near her eye the intricate necklace of sharp teeth contrasts with her playful yet regal expression a subtle onomatopoeia hinted through her softly puckered lips evokes a gentle kiss sound amplifying her charm
Negative Prompt
blurry, cropped, ugly
Prompt
two young women stand side by side , one has dark curly hair, wearing a sleeveless top and shorts with a belt, the other has long blonde hair, wearing similar attire, they exchange a subtle, knowing glance, as if sharing an unspoken understanding
Negative Prompt
blurry, cropped, ugly
Prompt
a haunting figure with green eyes framed by soft orange-blonde hair, gently caresses her lips, neon palette of pinks purples and blues creates an eerie glow around her the background dissolves into surreal drips
Negative Prompt
blurry, cropped, ugly
Prompt
striking beautiful summer young woman, swearing, hot, she dress a minuscule, elaborated and intricate tentacles gown
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: 17
  • Training steps: 10840
  • Learning rate: 2.5e-05
    • Learning rate schedule: polynomial
    • Warmup steps: 1084
  • Max grad norm: 0.01
  • Effective batch size: 6
    • Micro-batch size: 6
    • Gradient accumulation steps: 1
    • Number of GPUs: 1
  • Gradient checkpointing: True
  • Prediction type: flow-matching (extra parameters=['flux_schedule_auto_shift', 'shift=0.0', 'flux_use_uniform_schedule'])
  • Optimizer: adamw_bf16
  • Trainable parameter precision: Pure BF16
  • Caption dropout probability: 10.0%

LyCORIS Config: 

{
    "bypass_mode": true,
    "algo": "lokr",
    "multiplier": 1.0,
    "full_matrix": true,
    "linear_dim": 10000,
    "linear_alpha": 1,
    "factor": 4,
    "apply_preset": {
        "target_module": [
            "Attention",
            "FeedForward"
        ],
        "module_algo_map": {
            "FeedForward": {
                "factor": 4
            },
            "Attention": {
                "factor": 2
            }
        }
    }
}

Datasets

BESCH-CROP-SD35M-V04-512

  • Repeats: 1
  • Total number of images: 99
  • Total number of aspect buckets: 3
  • Resolution: 0.262144 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-CROP-SD35M-V04-768

  • Repeats: 1
  • Total number of images: 98
  • 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-SD35M-V04-1024

  • Repeats: 1
  • Total number of images: 99
  • Total number of aspect buckets: 1
  • Resolution: 1.048576 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-CROP-SD35M-V04-1280

  • Repeats: 1
  • Total number of images: 99
  • Total number of aspect buckets: 1
  • Resolution: 1.6384 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-MIX-SD35M-V04-512

  • Repeats: 1
  • Total number of images: 93
  • 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-SD35M-V04-768

  • Repeats: 1
  • Total number of images: 90
  • Total number of aspect buckets: 8
  • Resolution: 0.589824 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-MIX-SD35M-V04-1024

  • Repeats: 1
  • Total number of images: 88
  • Total number of aspect buckets: 6
  • Resolution: 1.048576 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-MIX-SD35M-V04-1280

  • Repeats: 1
  • Total number of images: 85
  • Total number of aspect buckets: 8
  • Resolution: 1.6384 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-COVER-SD35M-V04-512

  • Repeats: 2
  • Total number of images: 86
  • Total number of aspect buckets: 1
  • Resolution: 0.262144 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-COVER-SD35M-V04-768

  • Repeats: 2
  • Total number of images: 83
  • Total number of aspect buckets: 6
  • Resolution: 0.589824 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-COVER-SD35M-V04-1024

  • Repeats: 2
  • Total number of images: 81
  • Total number of aspect buckets: 3
  • Resolution: 1.048576 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-COVER-SD35M-V04-1280

  • Repeats: 2
  • Total number of images: 83
  • Total number of aspect buckets: 1
  • Resolution: 1.6384 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-COVER-SD35M-V04-1536

  • Repeats: 2
  • Total number of images: 83
  • Total number of aspect buckets: 1
  • Resolution: 2.359296 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-ORIGINAL-SD35M-V04-512

  • Repeats: 1
  • Total number of images: 68
  • Total number of aspect buckets: 2
  • Resolution: 0.262144 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-ORIGINAL-SD35M-V04-768

  • Repeats: 1
  • Total number of images: 68
  • Total number of aspect buckets: 2
  • Resolution: 0.589824 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

BESCH-ORIGINAL-SD35M-V04-1024

  • Repeats: 1
  • Total number of images: 68
  • Total number of aspect buckets: 3
  • Resolution: 1.048576 megapixels
  • Cropped: True
  • Crop style: random
  • Crop aspect: closest
  • Used for regularisation data: No

Inference 

import torch
from diffusers import DiffusionPipeline
from lycoris import create_lycoris_from_weights


def download_adapter(repo_id: str):
    import os
    from huggingface_hub import hf_hub_download
    adapter_filename = "pytorch_lora_weights.safetensors"
    cache_dir = os.environ.get('HF_PATH', os.path.expanduser('~/.cache/huggingface/hub/models'))
    cleaned_adapter_path = repo_id.replace("/", "_").replace("\\", "_").replace(":", "_")
    path_to_adapter = os.path.join(cache_dir, cleaned_adapter_path)
    path_to_adapter_file = os.path.join(path_to_adapter, adapter_filename)
    os.makedirs(path_to_adapter, exist_ok=True)
    hf_hub_download(
        repo_id=repo_id, filename=adapter_filename, local_dir=path_to_adapter
    )

    return path_to_adapter_file
    
model_id = 'stabilityai/stable-diffusion-3.5-medium'
adapter_repo_id = 'gattaplayer/besch-style-st-sd35m-lokr-25e-6-bs6-v04'
adapter_filename = 'pytorch_lora_weights.safetensors'
adapter_file_path = download_adapter(repo_id=adapter_repo_id)
pipeline = DiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.bfloat16) # loading directly in bf16
lora_scale = 1.0
wrapper, _ = create_lycoris_from_weights(lora_scale, adapter_file_path, pipeline.transformer)
wrapper.merge_to()

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 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,
    negative_prompt=negative_prompt,
    num_inference_steps=30,
    generator=torch.Generator(device='cuda' if torch.cuda.is_available() else 'mps' if torch.backends.mps.is_available() else 'cpu').manual_seed(1121925699670477),
    width=832,
    height=1216,
    guidance_scale=4.0,
    skip_guidance_layers=[7, 8, 9],
).images[0]
image.save("output.png", format="PNG")
Downloads last month
17
Inference Examples
Text-to-Image
Examples
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for gattaplayer/besch-style-st-sd35m-lokr-25e-6-bs6-v04

Base model

stabilityai/stable-diffusion-3.5-medium
Adapter
(59)
this model