AI Provider for Hugging Face
| 开发者 | aslamdoctor |
|---|---|
| 更新时间 | 2026年4月14日 12:21 |
| PHP版本: | 7.4 及以上 |
| WordPress版本: | 7.0 |
| 版权: | GPL-2.0-or-later |
| 版权网址: | 版权信息 |
详情介绍:
- Registers Hugging Face on the Settings > Connectors admin screen
- Supports API key management (environment variable, PHP constant, or database)
- Text generation via
wp_ai_client_prompt() - Image generation via
wp_ai_client_prompt()->generate_image() - Dynamically fetches top 20 popular models from HuggingFace (updated every 12 hours)
- Multi-provider support — automatically routes to the best available inference provider (hf-inference, fal-ai, replicate, together, nscale, wavespeed)
- Add custom models from the Settings > Hugging Face admin page
- Extensible model lists via
hugging_face_ai_provider_modelsandhugging_face_ai_provider_image_modelsfilters - Configurable base URL for self-hosted TGI instances
- Clear, actionable error messages for common API issues
安装:
- Upload the plugin to the
/wp-content/plugins/ai-provider-for-hugging-facedirectory. - Activate the plugin through the 'Plugins' menu in WordPress.
- Go to Hugging Face Tokens and create a new Access Token with Read permission.
- Go to Settings > Connectors and enter your Hugging Face API token.
屏幕截图:
常见问题:
Which models are supported?
The plugin dynamically fetches the top 20 most popular text and image generation models from HuggingFace, updated every 12 hours. You can also add any model via the Custom Models field in Settings > Hugging Face, or using the hugging_face_ai_provider_models and hugging_face_ai_provider_image_models filters.
Do I need to pay for HuggingFace?
Models on the free "hf-inference" provider work without credits. Other providers (fal-ai, replicate, etc.) require pre-paid HuggingFace credits. The plugin automatically selects the best available provider, preferring the free tier.
Can I use a self-hosted model?
Yes. Use the hugging_face_ai_provider_base_url filter for text generation or hugging_face_ai_provider_image_url filter for image generation to point to your own inference instance.
What capabilities are supported?
Text generation and image generation. Video generation support may be added in future versions.
更新日志:
- Fetch models from all HuggingFace inference providers instead of warm-only models.
- Filter text generation models to chat-compatible (conversational) models only.
- Show pricing labels in model dropdowns: "Free tier", "from $X.XX/M tokens", or "Paid".
- Models under $0.10/M tokens and hf-inference models are labelled "Free tier".
- Update fallback model lists with broadly supported models for better reliability.
- Initial release.
- Connector registration with API key management.
- Text generation via Hugging Face Inference API.
- Image generation via text-to-image models with multi-provider support.
- Dynamic model lists fetched from HuggingFace API.
- Admin page with custom model management (add/remove with instant dropdown sync).
- Clear error messages for 400, 401, 402, 404, 410, 422, 429, 500, 503 API responses.