Skip to content

使用CogVideoX 1.5运行Gradio Demo时出现张量不匹配 #784

@yschdxm

Description

@yschdxm

System Info / 系統信息

Cuda:12.9
Diffusers:0.34.0
Python:3.10.18
系统:Windows 11 专业版 24H2 26100.4484

Information / 问题信息

  • The official example scripts / 官方的示例脚本
  • My own modified scripts / 我自己修改的脚本和任务

Reproduction / 复现过程

运行Gradio Demo并使用I2V生成视频(使用任何图片),发生以下报错(张量不匹配)

发生异常: RuntimeError
Sizes of tensors must match except in dimension 1. Expected size 16 but got size 8 for tensor number 1 in the list.
File "F:\UPC\YNU\CogVideo\inference\gradio_composite_demo\app.py", line 252, in infer
video_pt = pipe_image(
File "F:\UPC\YNU\CogVideo\inference\gradio_composite_demo\app.py", line 464, in generate
latents, seed = infer(
RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 16 but got size 8 for tensor number 1 in the list.

Expected behavior / 期待表现

正常生成视频

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions