FLUX.1 Dev LoRA MiaoKa Yarn World

🚀 FLUX.1-dev-LoRA-MiaoKa-Yarn-World

这是一个基于 MIAOKA 在 FLUX.1-dev 上训练的 LoRA（MiaoKa-Yarn-World）模型，用于创作毛线艺术作品。它能够生成复杂逼真的毛线纹理和图案，同时保持高性能。

🚀 快速开始

触发词

你应该使用 mkym this is made of wool 来触发图像生成。在 diffusers 中，推荐的缩放比例是 0.8 到 1.0。

推理代码示例

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/FLUX.1-dev-LoRA-MiaoKa-Yarn-World", weight_name="FLUX-dev-lora-MiaoKa-Yarn-World.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "mkym this is made of wool, sports car"

image = pipe(prompt, 
             num_inference_steps=24, 
             guidance_scale=3.5,
            ).images[0]
image.save(f"example.png")

在线推理

你也可以在 Shakker AI 下载此模型，我们在那里提供了一个在线界面来生成图像。

✨ 主要特性

该模型能够生成复杂且逼真的毛线纹理和图案，同时保持高性能，可用于创作毛线艺术作品。

💻 使用示例

基础用法

import torch
from diffusers import FluxPipeline

pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16)
pipe.load_lora_weights("Shakker-Labs/FLUX.1-dev-LoRA-MiaoKa-Yarn-World", weight_name="FLUX-dev-lora-MiaoKa-Yarn-World.safetensors")
pipe.fuse_lora(lora_scale=1.0)
pipe.to("cuda")

prompt = "mkym this is made of wool, sports car"

image = pipe(prompt, 
             num_inference_steps=24, 
             guidance_scale=3.5,
            ).images[0]
image.save(f"example.png")

📚 详细文档

展示