feat: doubao add first and last image to video - #2756
Conversation
WalkthroughA new Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Actionable comments posted: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
relay/channel/task/doubao/adaptor.go (1)
224-244: Add validation to prevent data: URLs from being used as image inputs.Images from
req.Images(lines 226-233) should be validated to prevent data: URLs, consistent with the pattern used incontroller/task_video.goandvertex/adaptor.go. Data: URLs containing base64-encoded data should not be processed through the doubao API.Additionally, the new
Rolefield enables first/last frame video generation, but images added viareq.Imagesdon't have theirRoleset. Since metadata is unmarshaled directly into the requestPayload struct (line 241), users must specify content items with explicit role values through metadata rather than usingreq.Images.
…65bf72572ff8684dd7ef068e576 feat: doubao add first and last image to video
豆包视频支持首尾帧生视频, 增加role字段

文档: https://www.volcengine.com/docs/82379/1520757
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.