feat(alibaba): add DashScope wan3.0-video provider and @hypit/alibaba-video model - #203
Closed
lucasclark7699-bot wants to merge 1 commit into
Closed
lucasclark7699-bot wants to merge 1 commit into
lucasclark7699-bot wants to merge 1 commit into
Conversation
- alibaba-video: fragment/surface 对齐当前 Distribution API,改用 createExactModelPrimaryGenerationFragment + sealGenerationRequestDraft,修复 @hypit/elaborator 不导出 createAssembledGenerationFragment 导致 CLI 加载失败 - alibaba-video: 端口表移除单端口 atMostOneOf(该约束至少需 2 个端口) - provider-wanx: parameters.duration 改为整数(DashScope 要求),新增 firstNumber 读取 number 端口值 - alibaba-wanx: 新增 demo.svrun 作为 Run Source(build 需吃 .svrun,.svml 是 Author Source) - 默认模型 wan3.0-video;本地实测 Build complete 并已导出视频
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds Alibaba Cloud DashScope video generation support to Hypit, wired end-to-end and verified locally (a real video was generated and exported).
What is included
packages/alibaba-video- the Model + SVML Surface (@hypit/alibaba-video, capabilityalibaba-qwen-vvg) with<alibaba:TextVideo>and<alibaba:ReferenceVideo>surfaces. Ports: prompt, duration, resolution, aspectRatio, referenceImage.createExactModelPrimaryGenerationFragment+sealGenerationRequestDraft), matching@hypit/seedance.packages/provider-wanx- the missing Endpoint/Provider that actually calls DashScope (wan3.0-video): async submit to video-synthesis with X-DashScope-Async, poll the task, then collect output.video_url.alibaba-wanx/- a minimal working example: demo.svml (Author Source) + demo.svrun (Run Source) + hypit.runtime.json.Verification
Local end-to-end:
hypit build alibaba-wanx/demo.svrun --runtime alibaba-wanx/hypit.runtime.json --followreached Build complete (~2m20s), and the resulting video was exported successfully.Notes
wan3.0-video(configurable in hypit.runtime.json).parameters.durationto be an integer; sending a string fails validation. Calling this out because it cost real debugging time.atMostOneOf, which the Distribution rejects (it needs at least two ports); removed.createAssembledGenerationFragmentfrom@hypit/elaborator, which the current Distribution does not export; rewritten.Happy to adjust naming, packaging or the default model to match upstream conventions.