🚀 Flux-Midjourney-Painterly-LoRA
Flux-Midjourney-Painterly-LoRA 是一個文本到圖像的模型，基於 LoRA 和 Diffusers 技術，能夠根據特定提示生成具有繪畫風格的圖像，為圖像創作帶來新的可能。
🚀 快速開始
環境設置
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-Midjourney-Painterly-LoRA"
trigger_word = "mj painterly"
pipe.load_lora_weights(lora_repo)
device = torch.device("cuda")
pipe.to(device)
觸發詞使用
你應該使用 mj painterly 來觸發圖像生成。
模型下載
此模型的權重以 Safetensors 格式提供。
點擊下載，可在 Files & versions 標籤中獲取。
✨ 主要特性
- 支持文本到圖像的轉換，能夠根據不同的文本提示生成多樣化的圖像。
- 採用 LoRA 技術，可高效微調模型。
- 提供多個示例，展示了不同風格和主題的圖像生成效果。
📚 詳細文檔
模型描述
圖像處理參數
| 參數 |
值 |
參數 |
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 |
25 & 3400 |
| Epoch |
20 |
Save Every N Epochs |
1 [40] |
標註信息
標註採用 florence2 - en（自然語言 & 英語）。
訓練數據
總共使用 26 張 [Midjourney 生成的合成圖像] 進行訓練。
最佳尺寸與推理
| 尺寸 |
寬高比 |
推薦情況 |
| 1280 x 832 |
3:2 |
最佳 |
| 1024 x 1024 |
1:1 |
默認 |
推理範圍
📄 許可證
本模型使用的許可證為 flux - 1 - dev - non - commercial - license，詳細信息請查看 許可證鏈接。
🔍 示例展示
以下是一些輸入文本及對應的輸出圖像示例：
- **輸入文本**：'mj painterly, a monochromatic drawing of a womans face is displayed against a dark blue backdrop. The womans head is angled towards the left side of the frame, her hair cascading over her shoulders. Her eyes are closed, her lips are pursed, and her nose is adorned with a nose ring. Her hair is cut in a bob, adding a touch of depth to the composition.'
**輸出圖像**：[點擊查看](images/111.png)
- **輸入文本**：'mj painterly, An animated portrait of a woman with a white t - shirt on a light pink background. The womans head is facing the left side of the frame, her hair is a vibrant shade of blue, with a few wispy bangs on the right side of her head. Her eyebrows are a darker shade of brown, and her lips are a lighter shade of pink. Her eyes are a piercing blue, and she has a slight smile on her face. Her hair is pulled back, framing her face, adding a pop of color to the scene. The background is a pale pink, creating a stark contrast to the womans face.'
**輸出圖像**：[點擊查看](images/222.png)
- **輸入文本**：'mj painterly, An animated image of a woman with short green hair. The womans hair is a vibrant shade of green, while her lips are a lighter shade of pink. Her eyes are a darker shade of brown. Her eyebrows are a light shade of red. She is wearing a short sleeve green t - shirt. The background is a light green, and there is a shadow of her head on the right side of the image.'
**輸出圖像**：[點擊查看](images/333.png)
- **輸入文本**：'mj painterly, An animated portrait of a woman with long white hair. The woman is wearing a blue dress with a white collar. The background is a light blue color.'
**輸出圖像**：[點擊查看](images/444.png)
- **輸入文本**：'mj painterly, A monochromatic drawing of a cat curled up in a sleeping position on a dark teal background. The cats fur is a gradient of greys, and its ears are perked slightly as if listening in sleep. A long tail loops around its body, and the texture of the fur is rendered in delicate strokes, adding depth and softness to the composition.'
**輸出圖像**：[點擊查看](images/555.png)
- **輸入文本**：'mj painterly, An animated portrait of a woman with curly orange hair styled in a messy bun. She is wearing a mustard yellow turtleneck sweater. Her freckles are prominent, and her eyes are green and wide. The background is a soft beige with light sketchy shading around her form.'
**輸出圖像**：[點擊查看](images/666.png)
%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 支持多種語言