🚀 NFT-Plus-InsideOut-Perspective模型
本模型主要用于文本到图像的转换，借助LoRA和Diffusers技术，能根据特定的文本描述生成富有创意的NFT图像，为艺术创作和NFT设计提供了强大的工具。
🚀 快速开始
模型设置
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 = "strangerzonehf/NFT-Plus-InsideOut-Perspective"
trigger_word = "NFT ++"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
触发词使用
你需要使用 NFT ++ 来触发图像生成。
✨ 主要特性
- 支持文本到图像的转换，可根据输入的文本描述生成独特的NFT图像。
- 利用LoRA和Diffusers技术，提升模型的灵活性和性能。
📦 安装指南
文档未提供具体安装步骤，暂不展示。
💻 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 = "strangerzonehf/NFT-Plus-InsideOut-Perspective"
trigger_word = "NFT ++"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
高级用法
文档未提供高级用法示例，暂不展示。
📚 详细文档
模型描述
图像生成示例
| 输入文本 |
输出图像 |
| 'NFT ++, An eye-level view of a glass milk carton with the words "prithivml" written on it in black letters. The carton is filled with a few dark gray clouds, and there is a white barcode on the left side of the carton. The background is a light blue color.' |
查看 |
| 'NFT++, A quirky cartoon depiction of a glass cube labeled "prithivmods" in bold white letters. The container is filled with tiny, glowing Polaroid photos floating in a transparent blue liquid. Each photo features a different miniature scene, such as sunsets and faces. A barcode wraps around the bottom left corner of the cube. The background is a gradient of pink and orange, evoking nostalgia.' |
查看 |
| 'NFT++, A detailed cartoon drawing of glass cube labeled "hf.co" in bold white letters. Inside, a shimmering liquid with hues of blue, purple, and silver flows, dotted with tiny glowing particles resembling stars. A barcode is seamlessly integrated into the container’s sleek design on the back. The background is a midnight blue gradient, adding a celestial feel' |
查看 |
| 'NFT ++, Captured on a light pink background, a cartoon drawing of a glass container with the word "prithiv-hf" written on it in black letters. The container is filled with a clear liquid, and there are brown bandages inside of the container. There is a barcode on the left side of the box, and a white bar code on the right side. The background is a solid pink.' |
查看 |
| 'NFT ++, a black and white drawing of a black swan in a glass container. The container is shaped like a hexagon, with a black handle on the right side. The swan is swimming in the water, its head facing towards the left side of the container, its beak slightly open. The water in the container is a dark blue, with white splashes on it. Above the swan, the words "prithiv-hf" are written in bold black letters. The background is a light blue, and the text "prithiv-hf" is written in a bold black font.' |
查看 |
| 'NFT ++, a cartoon drawing of a cats face is seen in a clear glass container. The container is filled with a variety of brown objects, including a barcode and the word "prithiv" written in black letters. The background is a stark white, with a light brown border. The cats head is adorned with a red ribbon, adding a pop of color to the scene. The word "imo" is written on the top right corner of the container.' |
查看 |
图像参数
| 属性 |
详情 |
| 基础模型 |
black-forest-labs/FLUX.1-dev |
| 触发词 |
NFT ++ |
| 许可证 |
creativeml-openrail-m |
图像生成参数
| 参数 |
值 |
参数 |
值 |
| LR调度器 |
constant |
噪声偏移 |
0.03 |
| 优化器 |
AdamW |
多分辨率噪声折扣 |
0.1 |
| 网络维度 |
64 |
多分辨率噪声迭代次数 |
10 |
| 网络Alpha |
32 |
重复与步数 |
12 & 2100 |
| 轮数 |
11 |
每N轮保存一次 |
1 |
标注信息
标注采用florence2-en（自然语言 & 英语）。
训练图像总数
总共使用了12张图像进行训练。
最佳尺寸与推理
| 尺寸 |
纵横比 |
推荐情况 |
| 1280 x 832 |
3:2 |
最佳 |
| 1024 x 1024 |
1:1 |
默认 |
推理范围
🔧 技术细节
文档未提供具体技术细节，暂不展示。
📄 许可证
本模型使用的许可证为creativeml-openrail-m。
📥 下载模型
本模型的权重以Safetensors格式提供。
点击下载（在文件与版本标签中）。
数据来源
数据来源为quaphadoodle。
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Transformers Supports Multiple Languages