当前位置: 首页 > news >正文

LLMS-Stable diffusion 报错 index out of bounds

问题:Stable diffusion 报错 index out of bounds

  • 1、先看日志
  • 2、问题原因
  • 3、解决方法
    • 3-1:cmd键入命令查看本机CUDA版本
  • 4、安装过程

1、先看日志

这个错一般是在同学使用Stable diffusion时,文生视频的操作中爆出来了。

2024-10-19 21:15:04,709 - AnimateDiff - INFO - AnimateDiff process start.
2024-10-19 21:15:04,710 - AnimateDiff - INFO - Loading motion module mm_sd_v15_v2.ckpt from H:\AI\sd-webui-aki-v4.9.7\extensions\sd-webui-animatediff\model\mm_sd_v15_v2.ckpt
2024-10-19 21:15:06,367 - AnimateDiff - INFO - Guessed mm_sd_v15_v2.ckpt architecture: MotionModuleType.AnimateDiffV2
2024-10-19 21:15:10,580 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet middle block.
2024-10-19 21:15:10,580 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet input blocks.
2024-10-19 21:15:10,580 - AnimateDiff - INFO - Injecting motion module mm_sd_v15_v2.ckpt into SD1.5 UNet output blocks.
2024-10-19 21:15:10,580 - AnimateDiff - INFO - Setting DDIM alpha.
2024-10-19 21:15:10,591 - AnimateDiff - INFO - Injection finished.
2024-10-19 21:15:10,591 - AnimateDiff - INFO - AnimateDiff + ControlNet will generate 16 frames.
2024-10-19 21:15:12,926 - AnimateDiff - INFO - inner model forward hooked
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [32,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [33,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [34,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [35,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [36,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [37,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [38,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [39,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [40,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [41,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [837,0,0], thread: [42,0,0] Assertion `-sizes[i] <= index && index < sizes[i] && "index out of bounds"` failed.
C:\actions-runner\_work\pytorch\pytorch\builder\windows\pytorch\aten\src\ATen\native\cuda\IndexKernel.cu:92: block: [83

http://www.mrgr.cn/news/54302.html

相关文章:

  • string
  • 【详解】下载MySql安装教程(帮助数据库下载)
  • 导出Excel的常用方法:从前端到后端的全面指南
  • 【MySQL】提高篇—事务管理:事务隔离级别的介绍
  • 394.字符串解码
  • java的第一个游戏界面
  • 调整奇数偶数的顺序
  • 正则表达式 - 修饰符
  • 【C++贪心 单调栈】1727. 重新排列后的最大子矩阵|1926
  • 数据分箱:决策树得到特征的分箱区间后后怎么映射到原数据中?
  • cs61a涉及图像转换的代码注释(Lecture01)
  • 高效的多进程编程:使用 Python `multiprocessing` 库进行进程管理
  • Lucas带你手撕机器学习——线性回归
  • golang 基本数据类型
  • 基于DNA算法的遥感图像加解密matlab仿真
  • 衡石分析平台系统分析人员手册-可视化报表仪表盘
  • 定时发送邮件
  • 【STM32-HAL库】STM32F系列新建工程并点灯教程(小白向)
  • Docker本地镜像发布到Docker Registry私有仓库
  • 从人工智能到大模型的演变
  • 基于FPGA的信号发生器verilog实现,可以输出方波,脉冲波,m序列以及正弦波,可调整输出信号频率
  • 【海图界面上一些常见术语UTC、HDG、COG、SOG、LAT、LON的基本解释】
  • Java | Leetcode Java题解之第494题目标和
  • 测试主分支
  • 使用 Python 解析火狐浏览器的 SQLite3 数据库
  • 基于python+dj+mysql的音乐推荐系统网页设计