Cogvideox

[jiangbo721]

Summary

The old cogvideo generates videos by submitting the task only, and the result is fetched only once, without waiting until the task succeeds or fails. So the old cogvideo is not work, so I rewrote a cogvideox tool based on the official docs.

Tip

Close issue syntax: Fixes #<issue number> or Resolves #<issue number>, see documentation for more details.

Screenshots

Before	After

|

|

|

Checklist

Important

Please review the checklist below before submitting your pull request.

• This change requires a documentation update, included: Dify Document
• I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
• I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
• I've updated the documentation accordingly.
• I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods

[jiangbo721]

Doc: https://open.bigmodel.cn/dev/api/videomodel/cogvideox

[crazywoola]

Please be aware that we are going to roll out the v1.0.0 changes related to models runtimes and tools will not take effect above v1.0, please make sure adapt the changes to https://github.com/langgenius/dify-official-plugins. :)