🚀 flux_lora_meme_v2

flux_lora_meme_v2是一个文本到图像的模型，借助AI Toolkit进行训练，可生成具有幽默夸张风格的图像，适用于多种图像生成工具。

🚀 快速开始

下载模型

此模型的权重以Safetensors格式提供。你可以在Files & versions标签页下载。可配合ComfyUI、AUTOMATIC1111、SD.Next、Invoke AI等工具使用。

使用🧨 diffusers库

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")

更多细节，包括LoRA的加权、合并和融合等内容，请查看diffusers中加载LoRA的文档。

✨ 主要特性

• 文本到图像生成：根据输入的文本描述，生成对应的图像。
• 幽默夸张风格：生成的图像具有幽默夸张的效果，如惊讶的柴犬、震惊的花猫等场景。
• 多工具兼容：可与ComfyUI、AUTOMATIC1111、SD.Next、Invoke AI等图像生成工具配合使用。

💻 使用示例

基础用法

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")

高级用法

# 可根据文档中关于LoRA的加权、合并和融合等高级操作进行代码编写
# 这里仅为示例，具体操作需参考文档
# 例如进行LoRA的加权操作
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)  # 设置加权系数
image = pipeline('A surprised or shocked Shiba Inu...').images[0]
image.save("weighted_image.png")

📚 详细文档

触发词

本模型未定义触发词。

示例展示

📄 许可证

本模型使用flux-1-dev-non-commercial-license许可证。