🚀 Flux DreamBooth LoRA - data-is-better-together/image-preferences-flux-dev-lora
Flux DreamBooth LoRA是基于特定数据集训练的模型,可用于文本到图像的生成任务,为图像创作提供了多样化的选择。
🚀 快速开始
你可以按照以下步骤快速使用该模型进行图像生成:
- 下载模型的LoRA权重文件。
- 使用
diffusers
库加载基础模型和LoRA权重。
- 输入触发词进行图像生成。
✨ 主要特性
- 多风格支持:支持多种图像风格,如
Cinematic
(电影风格)、Photographic
(摄影风格)、Anime
(动漫风格)等。
- 基于DreamBooth训练:使用DreamBooth技术进行训练,能够更好地学习特定概念。
- 与diffusers库集成:可以方便地与
diffusers
库结合使用。
📦 安装指南
本README未提及具体安装步骤,若要使用该模型,可参考以下通用步骤:
- 确保你已经安装了
diffusers
库:
pip install diffusers
- 安装其他依赖库,如
torch
等:
pip install torch
💻 使用示例
基础用法
from diffusers import AutoPipelineForText2Image
import torch
pipeline = AutoPipelineForText2Image.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to('cuda')
pipeline.load_lora_weights('davidberenstein1957/image-preferences-flux-dev-lora', weight_name='pytorch_lora_weights.safetensors')
image = pipeline('["Cinematic", "Photographic", "Anime", "Manga", "Digital art", "Pixel art", "Fantasy art", "Neonpunk", "3D Model", “Painting”, “Animation” “Illustration”]').images[0]
高级用法
对于更多细节,包括LoRA的加权、合并和融合等操作,请查看diffusers中加载LoRA的文档。
📚 详细文档
模型描述
这些是davidberenstein1957/image-preferences-flux-schnell-lora
的DreamBooth LoRA权重,适用于black-forest-labs/FLUX.1-schnell
。权重使用DreamBooth和Flux diffusers trainer进行训练。文本编码器的LoRA未启用。
触发词
你应该使用["Cinematic", "Photographic", "Anime", "Manga", "Digital art", "Pixel art", "Fantasy art", "Neonpunk", "3D Model", “Painting”, “Animation” “Illustration”]
来触发图像生成。
下载模型
在“Files & versions”标签中下载*.safetensors LoRA。
预期用途和限制
如何使用
限制和偏差
[TODO: provide examples of latent issues and potential remediations]
训练细节
[TODO: describe the data used to train the model]
📄 许可证
请遵守此处描述的许可条款。
🔍 示例展示
输入文本 |
输出图像 |
a bustling manga street, devoid of vehicles, detailed with vibrant colors and dynamic line work, characters in the background adding life and movement, under a soft golden hour light, with rich textures and a lively atmosphere, high resolution, sharp focus |
点击查看 |
a boat in the canals of Venice, painted in gouache with soft, flowing brushstrokes and vibrant, translucent colors, capturing the serene reflection on the water under a misty ambiance, with rich textures and a dynamic perspective |
点击查看 |
A vibrant orange poppy flower, enclosed in an ornate golden frame, against a black backdrop, rendered in anime style with bold outlines, exaggerated details, and a dramatic chiaroscuro lighting. |
点击查看 |
Armored armadillo, detailed anatomy, precise shading, labeled diagram, cross-section, high resolution. |
点击查看 |
A photographic photo of a hedgehog in a forest 4k |
点击查看 |
Grainy shot of a robot cooking in the kitchen, with soft shadows and nostalgic film texture. |
点击查看 |
🏷️ 标签
- text-to-image
- diffusers-training
- diffusers
- lora
- flux
- flux-diffusers
- template:sd-lora
📊 数据集
- data-is-better-together/image-preferences-results-binarized
- data-is-better-together/open-image-preferences-v1-results