千问AI平台
Official@qianwen-ai · China
QianWen provides multimodal generation and analysis capabilities including video synthesis, image processing, speech synthesis, and text generation for enterprise environments.
Agent Skills by 千问AI平台
Showing 9 vetted skills indexed across 1 GitHub repositories.
QianWen-AIqianwen-video-generation
Automate video generation with Wan models across t2v, i2v, kf2v, r2v, and vace modes.
QianWen-AIqianwen-usage
Query QianWen authentication status and usage metrics via CLI.
QianWen-AIqianwen-model-selector
Select optimal Qwen models and parameters using QianWen CLI data.
QianWen-AIqianwen-vision
Analyze images and videos with Qwen Vision models for OCR and visual reasoning.
QianWen-AIqianwen-image-generation
Generate and edit images using Wan and Qwen Image models.
QianWen-AIqianwen-audio-tts
Synthesize speech from text using Qwen TTS models via the DashScope API.
QianWen-AIqianwen-ops-auth
Configure and validate QianWen API keys using environment variables and curl.
QianWen-AIqianwen-update-check
Compare local QianWen-AI skill pack version against GitHub releases.
QianWen-AIqianwen-text
Enable OpenAI-compatible chat, text generation, and tool calling for Qwen models.
Frequently Asked Questions About 千问AI平台
FAQPage SchemaWhat specific media generation tasks can be performed?▼
Users can generate video content using text-to-video, image-to-video, keyframe-to-video, and reference-to-video modes. Additionally, the platform supports image generation, image editing, and text-to-speech synthesis, alongside visual reasoning and optical character recognition for image and video analysis.
Which technical personas are the primary users?▼
The platform is designed for software engineers and developers integrating multimodal generative capabilities into enterprise applications. It targets professionals requiring programmatic access to vision, speech, and text generation models through standardized authentication and configuration patterns.
What are the prerequisites for runtime configuration?▼
Runtime configuration requires valid authentication credentials managed via environment variables. Users must validate their access status and configure model parameters to interface with the DashScope infrastructure, ensuring compatibility with standard chat and generation request formats.