🚀 3DXL Partfile 0002模型
3DXL Partfile 0002是一个用于图像生成的模型，结合了文本到图像、LoRA等技术，能够根据特定的文本提示生成高质量的3D风格图像。
🚀 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/Flux-3DXL-Partfile-0002"
trigger_word = "3DXLP2"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
触发图像生成
你应该使用 3DXLP2 来触发图像生成。
✨ 主要特性
- 文本到图像转换：根据输入的文本提示生成对应的3D风格图像。
- LoRA技术：通过低秩自适应（LoRA）技术，提高模型的训练效率和生成质量。
📦 安装指南
暂未提及具体安装步骤，可参考上述快速开始部分的代码示例进行设置。
💻 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-3DXL-Partfile-0002"
trigger_word = "3DXLP2"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
text_prompt = f"{trigger_word}, a man stands in front of a gray backdrop. He is dressed in a brown jacket, a black turtleneck, and a pair of black gloves."
image = pipe(text_prompt).images[0]
image.save("output_image.png")
📚 详细文档
模型描述
图像处理参数
| 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 |
23 & 3000 |
| Epoch |
20 |
Save Every N Epochs |
1 |
标注：florence2 - en（自然语言 & 英语）
训练使用的总图像数：19
最佳尺寸与推理
| 尺寸 |
宽高比 |
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
该模型基于 black-forest-labs/FLUX.1-dev 基础模型，使用LoRA技术进行微调。训练过程中使用了特定的图像处理参数，如LR Scheduler、Optimizer等，以优化模型性能。标注采用 florence2 - en 进行自然语言和英语标注，共使用了19张图像进行训练。在推理时，推荐使用特定的尺寸和推理步数，以获得最佳效果。
📄 许可证
本模型使用 creativeml-openrail-m 许可证。
模型下载
本模型的权重以Safetensors格式提供。
点击下载（在文件与版本选项卡中）。
示例图像
- 示例1
- 文本提示：3DXLP2, a man stands in front of a gray backdrop. He is dressed in a brown jacket, a black turtleneck, and a pair of black gloves. His hands are crossed over his chest, adding a touch of warmth to his outfit. His hair is short and receding, and his eyes are squinted. His mouth is slightly open, and he has a serious expression on his face.
- 输出图像：点击查看
- 示例2
- 文本提示：3DXLP2, A close-up shot of a womans face, taken from a low-angle perspective. The womans eyes are wide open, and her lips are pursed. She is wearing a black shirt, adorned with gold hoop earrings, and a gold necklace. Her hair is styled in a braided bun, and she is sporting a silver nose ring. The backdrop is a light gray, and the womans hair is pulled back in a ponytail.
- 输出图像：点击查看
- 示例3
- 文本提示：3DXLP2, a close-up shot of a mans face is featured prominently in the center of the frame. He is dressed in a red spiderman costume, adorned with a red and gold spiderman suit jacket. His hair is styled in a spiky manner, adding a touch of texture to his face. His eyes are a piercing blue, and his eyebrows are a darker shade of brown. His lips are a lighter shade of pink, and he has a slight smile on his lips. The backdrop is a light gray, and the mans shirt is adorned with golden spiderman webbing.
- 输出图像：点击查看
- 示例4
- 文本提示：3DXLP2, a close-up shot of a mans face features a goatee and a brown cowboy hat. His eyes are a piercing blue, and his eyebrows are a darker shade of brown. His lips are a lighter shade of pink, and he is wearing a blue collared button-down shirt with a white stripe down the collar. His hair is a light brown, and the hat is a dark brown. The background is blurred, but the sky is a soft gray.
- 输出图像：点击查看
%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