Flux Lora Meme V2

🚀 flux_lora_meme_v2

flux_lora_meme_v2是一個文本到圖像的模型，藉助AI Toolkit進行訓練，可生成具有幽默誇張風格的圖像，適用於多種圖像生成工具。

🚀 快速開始

下載模型

此模型的權重以Safetensors格式提供。你可以在Files & versions標籤頁下載。可配合ComfyUI、AUTOMATIC1111、SD.Next、Invoke AI等工具使用。

使用🧨 diffusers庫

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('longnthgmedia/flux_lora_meme_v2', weight_name='flux_lora_meme_v2.safetensors')
image = pipeline('A surprised or shocked Shiba Inu, sitting at a desk with its paws on a keyboard. Its wide eyes and open mouth convey an expression of intense surprise or panic, as if reacting to something unexpected on the computer screen. The background features a colorful, abstract painting reminiscent of \'The Scream\' by Edvard Munch, adding to the overall sense of dramatic tension. The combination of the dog\'s expression and the artistic backdrop creates a humorous and exaggerated scene, as if the Shiba Inu has just seen something shocking online.').images[0]
image.save("my_image.png")

更多細節，包括LoRA的加權、合併和融合等內容，請查看diffusers中加載LoRA的文檔。

✨ 主要特性

• 文本到圖像生成：根據輸入的文本描述，生成對應的圖像。
• 幽默誇張風格：生成的圖像具有幽默誇張的效果，如驚訝的柴犬、震驚的花貓等場景。
• 多工具兼容：可與ComfyUI、AUTOMATIC1111、SD.Next、Invoke AI等圖像生成工具配合使用。

💻 使用示例

基礎用法

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('longnthgmedia/flux_lora_meme_v2', weight_name='flux_lora_meme_v2.safetensors')
image = pipeline('A surprised or shocked Shiba Inu, sitting at a desk with its paws on a keyboard. Its wide eyes and open mouth convey an expression of intense surprise or panic, as if reacting to something unexpected on the computer screen. The background features a colorful, abstract painting reminiscent of \'The Scream\' by Edvard Munch, adding to the overall sense of dramatic tension. The combination of the dog\'s expression and the artistic backdrop creates a humorous and exaggerated scene, as if the Shiba Inu has just seen something shocking online.').images[0]
image.save("my_image.png")

高級用法

# 可根據文檔中關於LoRA的加權、合併和融合等高級操作進行代碼編寫
# 這裡僅為示例，具體操作需參考文檔
# 例如進行LoRA的加權操作
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('longnthgmedia/flux_lora_meme_v2', weight_name='flux_lora_meme_v2.safetensors', alpha=0.8)  # 設置加權係數
image = pipeline('A surprised or shocked Shiba Inu...').images[0]
image.save("weighted_image.png")

📚 詳細文檔

觸發詞

本模型未定義觸發詞。

示例展示

📄 許可證

本模型使用flux-1-dev-non-commercial-license許可證。