shengshu-ai

@shengshu-ai source repo

5 skills
0 followers
1 day ago last updated

▌
Vidu S1 API · shengshu-ai bundle
Integrate the Vidu S1 real-time interactive digital-human (数字人) streaming video API. Use this whenever the user is building against Vidu's live avatar service — creating a live session, joining the Aliyun RTC channel, driving the control WebSocket, handling NOT_READY retries, heartbeats, hangups, billing, or voice cloning. Trigger on mentions of Vidu S1, vidu live API, 数字人接入, /live/v1/lives, conn_init, live_bot, or "接入 vidu 实时数字人". Encodes the non-obvious protocol gotchas that the public doc gets wrong.

0
installs
▌
Vidu Skills · shengshu-ai bundle
Generate video and images by calling the official Vidu API via vidu CLI. Use when the user wants text-to-image, text-to-video, image-to-video, head-tail-image-to-video, reference-to-image, reference-to-video, lip-sync, text-to-speech, video-compose, Create References, or to submit or check Vidu tasks. Requires VIDU_TOKEN and optional VIDU_BASE_URL.

0
installs
▌
Debug World Model · shengshu-ai
Diagnoses training/inference failures in video world model pipelines. Triggers on: training hang, loss NaN, shape mismatch, NCCL timeout, SP bug, distillation collapse, half-video noise. Use when user describes a symptom and wants root-cause diagnosis.

0
installs
▌
Integrate New Backbone · shengshu-ai
Step-by-step recipe for plugging a new video DiT backbone into minWM, grounded in the HunyuanVideo (HY15) and Wan 2.1 reference integrations. Use when a user wants to add a new backbone to the framework.

0
installs
▌
Onboarding World Model · shengshu-ai
Onboarding guide for newcomers to video world model training in minWM. Covers two parts: Foundations (background theory for the two-phase pipeline) and Pitfalls (non-obvious mistakes from hands-on experience). Use when a newcomer is starting on controllable video generation training and needs background or wants to avoid common mistakes.

0
installs

5 published skills