metadata
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
- B&W
- Bold
- Shadows
- Color
widget:
- text: >-
Bold Shadows, Captured in a black and white monochromatic shot, a woman
stands in front of a backdrop of leaves and shadows. She is wearing a
black bra, her hair cascades over her shoulders. Her eyes are squinted and
her lips are pursed. Her hair is long and cascades in a ponytail, adding a
touch of movement to her face. The wall behind her is made up of white
tiles, creating a stark contrast to the womans body.
output:
url: images/BS1.png
- text: >-
Bold Shadows, Captured in a black and white monochromatic shot, a woman
stands in a short black dress, her long, wavy hair cascades over her
shoulders. The womans left leg is bent at the knee, while her right leg is
straight at the elbow. She is leaning against a wall, her left arm is
resting on the wall, adding a touch of balance to the scene. The sun is
shining down, creating a shadow on the right side of the image. To the
left of the woman, there are tall buildings, their windows reflecting off
of them.
output:
url: images/BS2.png
- text: >-
Bold Shadows, A black and white photograph of Candlelight, in the style of
street photography, with light projections casting bold shadows. The
contrast between her dark attire and the stark background creates a
striking visual impact. Her pose is dynamic yet confident, embodying
strength amid simplicity, buildings, wide angle
output:
url: images/BS3.png
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: Bold Shadows
license: creativeml-openrail-m
Bold-Shadows-Flux-LoRA
The model is still in the training phase. This is not the final version and may contain artifacts and perform poorly in some cases.
Model description
prithivMLmods/Bold-Shadows-Flux-LoRA
Image Processing Parameters
Parameter | Value | Parameter | Value |
---|---|---|---|
LR Scheduler | constant | Noise Offset | 0.03 |
Optimizer | AdamW | Multires Noise Discount | 0.1 |
Network Dim | 64 | Multires Noise Iterations | 10 |
Network Alpha | 32 | Repeat & Steps | 22 & 2440 |
Epoch | 10 | Save Every N Epochs | 1 |
Labeling: florence2-en(natural language & English)
Total Images Used for Training : 14
Best Dimensions
- 1024 x 1024 (Default)
Setting Up
import torch
from pipelines import DiffusionPipeline
base_model = "black-forest-labs/FLUX.1-dev"
pipe = DiffusionPipeline.from_pretrained(base_model, torch_dtype=torch.bfloat16)
lora_repo = "prithivMLmods/Bold-Shadows-Flux-LoRA"
trigger_word = "Bold Shadows"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
Trigger words
You should use Bold Shadows
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.