No. 4 of 25 ·AI Video Restoration Software

RestoraX

Web · Linux · Self-hosted · API

Freedom report

Two barsScore 6.4

Free tierA free tier is on its own pricing page
Open codeNo open-source code on record
Runs widely2 of 6 device platforms
DocumentedPlans, terms and facts published

RestoraX is an open-source toolkit for restoring old films, home videos and archival footage with video and audio processing models. It describes 25 models covering tasks such as upscaling, colorization, face restoration, frame interpolation, scratch and dust removal, deinterlacing, stabilization, SDR-to-HDR conversion and audio restoration. A visual pipeline builder connects processing steps with parallel branches, merge strategies, retry policies and progress tracking. Interfaces include a React web UI, a FastAPI REST API with WebSocket progress, a command-line interface and a ComfyUI node pack. The project is designed for self-hosting and documents Docker Compose setups for development and production. Third-party restorers can be added as separate PyPI plugins; model weights download from HuggingFace Hub on first use. The stated minimums are Python 3.11, 8 GB RAM, 5 GB disk and FFmpeg. CPU processing works; CUDA 12.1 or later with at least 8 GB of GPU VRAM is recommended. RestoraX is released under the MIT License.

Who it is for

RestoraX may suit people restoring films, home videos, anime, VHS recordings or newsreels who want a self-hosted toolkit. It also offers API, command-line and ComfyUI interfaces for different workflows.

What is good

Describes 25 video and audio restoration models
Visual pipeline builder supports branches and retries
Provides web, REST API, command-line and ComfyUI interfaces
Third-party restorers can be added as plugins

What to know first

Requires Python 3.11 and FFmpeg
Minimum requirements include 8 GB RAM and 5 GB disk
GPU recommendation requires CUDA 12.1 or later and 8 GB VRAM

Verdict

RestoraX brings multiple restoration tasks and interfaces into a self-hostable toolkit. Its stated software and hardware requirements are important to check before setting up a workflow.

RestoraX plans and pricing

All plans

RestoraX Free Open-source MIT software · self-hosted · GPU/CPU processing github.com · 3 Oct 2026

Compared on AI video restoration software

Free plan: Yes
Platform: web
Maximum upscale: 4x
Artifact removal: Yes
Frame interpolation: Yes
Face recovery: Yes

Best RestoraX alternatives

See all 20

One bar Vapourkit Free tier No. 1Free6.5 One bar Aiarty Video Enhancer Free tier No. 2$6.58/mo6.4 One bar Klarity Free tier No. 3Free6.4 One bar TensorPix Free tier No. 5$5.50/mo6.4 One bar HitPaw VikPea Paid plans No. 6$8.33/mo5.7 No signal Intelion Video Lab Paid plans No. 7—5.5

The record

Purpose: RestoraX is an open-source AI video and audio restoration toolkit for old films, home videos, and archival footage.
Restoration models: The project describes 25 models for super-resolution, colorization, face restoration, frame interpolation, scratch and dust removal, deinterlacing, stabilization, SDR-to-HDR conversion, and audio restoration.
Pipeline builder: Its visual pipeline builder uses a DAG engine with typed ports, parallel branches, merge strategies, retry policies, and per-branch progress.
Interfaces: RestoraX provides a React web UI, a FastAPI REST API with WebSocket progress, and a command-line interface.
ComfyUI: The project describes a ComfyUI node pack as part of its platform.
Integrations: The documented stack uses Celery and Redis for background jobs, PostgreSQL or SQLite for data storage, and MinIO in the production Docker setup.
Model weights: Model weights download automatically from HuggingFace Hub on first use.
Extensibility: Third-party restorers can be added through plugins distributed as separate PyPI packages.
Deployment: The maker documents Docker Compose setups for development and production and describes the software as self-hostable.
Requirements: The stated minimums include Python 3.11, 8 GB RAM, 5 GB disk, and FFmpeg; the page says CPU works and recommends CUDA 12.1 or later with 8 GB or more of GPU VRAM.
License: The repository is released under the MIT License, which grants use, modification, and distribution subject to its terms.
Security and compliance: The opened maker pages provide an MIT license but do not state a security certification or compliance standard.
Intended users: The README names old-film, home-video, archival-footage, anime, VHS, and newsreel restoration as use cases.
Price from: Free

Where it ranks on Freedom251

Best AI Video Restoration Software in 2026#4 of 25

Is RestoraX yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote RestoraX

Sources

github.com/karailker/restorax· checked 3 Oct 2026
github.com/karailker/restorax/blob/main/LICENSE· checked 3 Oct 2026