TencentARC
tencentarcTencentARC has one model in the ModelRunner catalog: GFPGAN, an Image-to-Image endpoint, priced at ≈$0.0017385 per image — face restoration: sharpen a blurry, low-resolution or compressed portrait.
1 public model — runnable in a free playground, through the REST API and JavaScript SDK, or from an AI assistant over MCP.
TencentARC models & pricing
What you can build with TencentARC models
- Face restoration: sharpen a blurry, low-resolution or compressed portrait GFPGAN
- Restore an old, faded or scratched family photo after scanning it GFPGAN
- Fix a smeared or distorted face in an AI-generated image GFPGAN
- Clean up a whole scanned picture, background included, not just the face GFPGAN
- Enlarge a small portrait while its facial detail is rebuilt GFPGAN
Browse by capability
Use TencentARC models from Claude & Cursor
Connect the ModelRunner MCP server once and your AI assistant can run every TencentARC model on this page as a tool — authorized via OAuth, results returned as hosted URLs in the conversation.
Claude Code
claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcpResearch, weights & licences
Frequently asked questions
What TencentARC models can I run on ModelRunner?
The catalog has 1 public TencentARC model: GFPGAN. It covers image-to-image. It has its own page with a free playground, the full input schema, and copy-paste code.
How much do TencentARC models cost?
Pay-per-use, with no subscription: the one TencentARC model billed per image costs around $0.0017385, and every page publishes its own rate — some are tiered, so a lower resolution or a shorter clip costs less per run. You buy credits and pay only for what you generate.
How do I call a TencentARC model from the API?
POST to https://queue.modelrunner.run/tencentarc/gfpgan with an Authorization: Key header and the input fields as the top-level JSON body (no wrapper object), then poll the returned status_url and fetch the result from response_url. The JavaScript SDK (@modelrunner/client) wraps that in a single subscribe() call, which is the one place an { input } object is used.
Can I run TencentARC model from Claude or Cursor?
Yes. Connect the ModelRunner MCP server (https://mcp.modelrunner.run/mcp) once and TencentARC's model becomes a tool your assistant can call with run_model — authorized over OAuth 2.1, so no API key goes into a config file. Results come back as hosted URLs in the conversation.
Where is the source code or paper for TencentARC models?
1 of the 1 TencentARC model in the catalog link their own upstream sources — GFPGAN — covering some combination of code repository, paper, weights and licence. The links are listed on this page and on each model's own page.
More on ModelRunner
Browse the full model catalog, compare live per-configuration rates on the pricing page, see curated sets on explore, or view every model creator.