FLUX.1 Dev LoRA MiaoKa Yarn World

🚀 FLUX.1-dev-LoRA-MiaoKa-Yarn-World

這是一個基於 MIAOKA 在 FLUX.1-dev 上訓練的 LoRA（MiaoKa-Yarn-World）模型，用於創作毛線藝術作品。它能夠生成複雜逼真的毛線紋理和圖案，同時保持高性能。

🚀 快速開始

觸發詞

你應該使用 mkym this is made of wool 來觸發圖像生成。在 diffusers 中，推薦的縮放比例是 0.8 到 1.0。

推理代碼示例

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")

在線推理

你也可以在 Shakker AI 下載此模型，我們在那裡提供了一個在線界面來生成圖像。

✨ 主要特性

該模型能夠生成複雜且逼真的毛線紋理和圖案，同時保持高性能，可用於創作毛線藝術作品。

💻 使用示例

基礎用法

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")

📚 詳細文檔

展示