tencentarc/gfpgan
Practical face restoration algorithm for *old photos* or *AI-generated faces*
Model Inputs
Input
GFPGAN version. v1.3: better quality. v1.4: more details and better identity.
Rescaling factor
Result
Pricing
tencentarc/
gfpgan
Pricing for Synexa AI models works differently from other providers. Instead of being billed by time, you are billed by input and output, making pricing more predictable.
For example, generating 100 requests costs about $0.08.
Check out our docs for more information about how per-request pricing works on Synexa.
| Provider | Price ($) | Saving (%) |
|---|---|---|
| Synexa | $0.0008 | - |
| replicate | $0.0017 | 52.9% |
Readme
GFPGAN is designed as a Practical Algorithm for Real-world Face Restoration.
GitHub Repository
We encourage you to explore the GFPGAN project on GitHub.
If you find GFPGAN helpful in your work, we would greatly appreciate your support by starring the GitHub Repository. Furthermore, we encourage you to recommend GFPGAN to your colleagues and friends who might benefit from it. Your support is valuable to the project's growth and visibility within the research community.
Publication
For comprehensive details about the GFPGAN algorithm, methodology, and experimental results, please refer to our research paper available on arXiv.
Contact Information
For any questions or inquiries regarding GFPGAN, please feel free to contact us via email at the following addresses: