🚀 Bold-Shadows-Flux-LoRA
Bold-Shadows-Flux-LoRA 是一款图像生成模型,可基于特定提示词生成具有鲜明阴影效果的黑白图像,目前仍在训练阶段。
🚀 快速开始
模型加载
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)
触发词使用
你应该使用 Bold Shadows
来触发图像生成。
模型下载
此模型的权重以 Safetensors 格式提供。
点击下载,可在 Files & versions 标签中获取。
✨ 主要特性
- 能够生成具有鲜明阴影效果的黑白图像。
- 基于特定的图像生成参数进行训练。
📦 安装指南
暂未提供具体的安装步骤,可参考上述快速开始部分的代码示例进行模型加载。
💻 使用示例
基础用法
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)
prompt = "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."
image = pipe(prompt).images[0]
image.save("generated_image.png")
📚 详细文档
模型描述
prithivMLmods/Bold-Shadows-Flux-LoRA
图像参数处理
参数 |
值 |
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 |
标注:florence2-en(自然语言 & 英语)
用于训练的总图像数:14
最佳尺寸
注意事项
⚠️ 重要提示
该模型仍处于训练阶段。这不是最终版本,可能包含伪影,并且在某些情况下性能不佳。
模型托管
- 托管地址🧨: https://huggingface.co/spaces/prithivMLmods/FLUX-LoRA-DLC
📄 许可证
本模型采用 creativeml-openrail-m 许可证。