🚀 Flux-Creative-Stocks-LoRA 模型
Flux-Creative-Stocks-LoRA 是一个文本到图像的模型，借助 LoRA 技术，可依据输入的文本生成创意图像。该模型在图像生成领域具有广泛应用，能满足多样化的创意需求。
🚀 快速开始
模型描述
此部分介绍了 Flux-Creative-Stocks-LoRA 模型的相关信息，包括图像生成示例、模型基础信息、图像生成参数等。
图像生成示例
以下是一些输入文本及对应的生成图像示例：
| 输入文本 |
生成图像 |
| 'Creative Stocks, A flat lay of four neatly folded blue fabric rolls arranged in a square pattern. Each roll has a white label reading "COMFY-COTTON" with a minimalist logo of a cotton plant. The backdrop is a soft beige fabric.' |
图像 1 |
| 'Creative Stocks, a medium-sized cardboard box is positioned against a stark white backdrop. The box is adorned with black text that reads "HOCUME 2MO RESERVED" and "MOD SOCKS". The boxs design features a blue sock and a yellow sock. The text is written in a bold, black font.' |
图像 2 |
| 'Creative Stocks, A medium shot of a brown cardboard box with the words "SCHROBELER" written in green on the top of the box. The box is placed on a white wooden surface. There is a yellow label on the box with a man and a dog on it. The man is wearing a yellow shirt and a hat. The dog is holding a black bottle with a black cap. The bottle has a black label with white letters that read "LEKKER" on the bottom of it.' |
图像 3 |
| 'Creative Stocks, Captured at eye-level on a vibrant green backdrop, two red boxes, each with the word "Tomatier" written in white on the left side of the box. The box on the right side is labeled "Snack" in black letters, while the box in the middle has "TOMATIER" written on it in white letters. The boxes are identical, with the same design as the one on the bottom left corner. Each box has a black design on it, adding a pop of color to the otherwise monochromatic image.' |
图像 4 |
| 'Creative Stocks, A stack of gray aluminum cans arranged neatly on a wooden table. Each can is labeled with the word "FUEL+BOOST" in bold red letters and features a small graphic of a lightning bolt. The background is softly blurred, showcasing warm orange tones.' |
图像 5 |
| 'Creative Stocks, A medium shot of a kraft paper bag with the words "FRESHLY ROASTED BEANS" in bold green letters. The bag has a clear window revealing coffee beans inside. It is placed on a white marble surface with a small potted plant in the blurred background.' |
图像 6 |
模型基础信息
- 基础模型：black-forest-labs/FLUX.1-dev
- 实例提示词：Creative Stocks
- 许可证：apache - 2.0
图像生成参数
| 参数 |
值 |
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 |
19 & 2370 |
| Epoch |
16 |
Save Every N Epochs |
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 24 张原始 8 位图像进行训练。
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 |
推理步数范围
📦 安装指南
此部分可参考代码示例进行环境和模型的设置。
💻 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/Flux-Creative-Stocks-LoRA"
trigger_word = "Creative Stocks"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
触发词
你应该使用 Creative Stocks 来触发图像生成。
📚 详细文档
模型下载
该模型的权重以 Safetensors 格式提供。
点击下载，可在“Files & versions” 标签中获取。
📄 许可证
本模型采用 apache - 2.0 许可证。
%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 支持多种语言