{"id":"hitsz-tmg-aigc-claw","name":"AIGC-Claw","af_score":37.8,"security_score":46.8,"reliability_score":22.5,"what_it_does":"AIGC-Claw is an end-to-end AI video generation system built around the OpenClaw platform. It turns a user’s idea into a complete video through a six-stage workflow: script generation, character design, storyboard/shot planning, reference image generation, video generation (image-to-video and text-to-video), and post-editing/assembly with transitions. It supports interactive user confirmation at each stage and multiple third-party model providers (e.g., DashScope, Seedream, Jimeng, Kling, DeepSeek, OpenAI, Gemini).","best_when":"You want a self-hostable, customizable creative pipeline where each stage’s artifacts can be inspected and approved, and you’re comfortable wiring API keys for multiple model providers.","avoid_when":"You need a standardized, well-documented public API/SDK with clear rate limits and robust error semantics, or you cannot accept the operational complexity of running FastAPI/Next.js and coordinating multiple external AI providers.","last_evaluated":"2026-03-30T13:24:47.069191+00:00","has_mcp":false,"has_api":true,"auth_methods":["Environment variables in .env for model provider API keys","Likely provider-specific API key auth for LLM/VLM/image/video endpoints"],"has_free_tier":false,"known_gotchas":["This is an orchestration workflow rather than a small single-purpose API; an agent must manage multi-stage state and artifact passing.","Multiple external providers/models are supported; model-specific failures can occur, and the README does not describe normalized error handling/retries across providers.","Interactive stage-by-stage confirmation is mentioned; an agent may need to emulate or automate user confirmation paths."],"error_quality":0.0}