feat: 适配 RTX 3090 (24GB) 环境优化

硬件迁移：从 RTX 5090 (32GB) 迁移到 RTX 3090 (24GB)

主要改动：
- 所有启动脚本和配置文件中的 /home/xsl/ 路径替换为 /home/ubuntu/
- 适配新的 24GB VRAM 环境

train_lora_parallel.py

@@ -6,7 +6,7 @@
 通过 ThreadPoolExecutor 控制并发数。
 
 用法:
-  python /home/xsl/change_hair/train_lora_parallel.py
+  python /home/ubuntu/change_hair/train_lora_parallel.py
 
 前提：step1 训练数据已准备好（data/train_material/<hid>/images/1_hairstyle/*.png）
 """
@@ -16,11 +16,11 @@ import time
 import subprocess
 from concurrent.futures import ThreadPoolExecutor, as_completed
 
-TRAIN_DIR = "/home/xsl/change_hair/data/train_material"
-KOHYA_WORKDIR = "/home/xsl/change_hair/project/kohya_ss_home/kohya_ss"
-BASE_MODEL = "/home/xsl/change_hair/project/onediff/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors"
-KOHYA_ACCEL = "/home/xsl/miniconda3/envs/kohya/bin/accelerate"
-LOG_DIR = "/home/xsl/change_hair/project/logs"
+TRAIN_DIR = "/home/ubuntu/change_hair/data/train_material"
+KOHYA_WORKDIR = "/home/ubuntu/change_hair/project/kohya_ss_home/kohya_ss"
+BASE_MODEL = "/home/ubuntu/change_hair/project/onediff/stable-diffusion-webui/models/Stable-diffusion/v1-5-pruned-emaonly.safetensors"
+KOHYA_ACCEL = "/home/ubuntu/miniconda3/envs/kohya/bin/accelerate"
+LOG_DIR = "/home/ubuntu/change_hair/project/logs"
 
 # 本次要训练的发型
 HAIRSTYLES = ["chang_tuoyuan", "chang_zhixian", "chang_huaban", "chang_xinxing"]