CodeFormer is an open-source PyTorch project for robust blind face restoration using a codebook lookup transformer, published with NeurIPS 2022 lineage. The GitHub repository provides training and inference scripts for face restoration, colorization, and inpainting, plus links to Hugging Face and Replicate demos for trying the models online.
CodeFormer is distributed as an open GitHub project; running inference requires your own GPU environment or third-party demo hosts linked from the README.
API access
Not confirmed
Is sczhou/codeformer right for you?
A good fit for
Researchers and developers restoring or enhancing facial images and old photos with the published CodeFormer checkpoints.
Before you choose
You manage conda dependencies, checkpoints, and compute; the repository documents local setup rather than a single vendor-hosted API product page.
Blind face restoration
CodeFormer packages research-grade face restoration models and scripts so developers can enhance degraded portraits using codebook-based transformers.
What it can do
Features & capabilities
Unknown is different from unavailable. Each fact carries its own evidence.
Capability
Value
Evidence
Checked
Paper lineage
Repository title references the NeurIPS 2022 CodeFormer blind face restoration work.
Facts sourced
2026-10-04
Use cases
README highlights face restoration, color enhancement, and inpainting example outputs.
Facts sourced
2026-10-04
Online demos
README badges link to Hugging Face Spaces and Replicate demos for CodeFormer.
Facts sourced
2026-10-04
Understand the total cost
sczhou/codeformer pricing & plans
Free
Free
CodeFormer is distributed as an open GitHub project; running inference requires your own GPU environment or third-party demo hosts linked from the README.
Access
CodeFormer is distributed as an open GitHub project; running inference requires your own GPU environment or third-party demo hosts linked from the README.
CodeFormer is an open-source PyTorch project for robust blind face restoration using a codebook lookup transformer, published with NeurIPS 2022 lineage. The GitHub repository provides training and inference scripts for face restoration, colorization, and inpainting, plus links to Hugging Face and Replicate demos for trying the models online.
Does sczhou/codeformer have a free plan?
CodeFormer is distributed as an open GitHub project; running inference requires your own GPU environment or third-party demo hosts linked from the README.. This record lists ongoing free access; check the plan limits before starting.
How much does sczhou/codeformer cost?
No paid monthly price is listed; this record treats the product as free to start. See the plan cards for entitlements, billing commitments and seat minimums.
Can I use sczhou/codeformer through an API?
Not confirmed. API access and subscription access may have different terms; consult the linked sources.
What should I check before choosing it?
You manage conda dependencies, checkpoints, and compute; the repository documents local setup rather than a single vendor-hosted API product page.
Price history
No retained pricing changes yet. A current price alone does not establish a historical trend.