Our take
Inactiveno commits in over a year- Activity
- 19
- Community
- 22
- Issues
- 21
- Pull requests
- 20
+33 stars in the last 30 days
Clarity Upscaler offers a flexible Stable Diffusion upscaling implementation, but its inactive maintenance and highly concentrated contributor history make it a cautious choice for long-term adoption.
Good fit if
- You already use Stable Diffusion, Cog, ComfyUI, or AUTOMATIC1111 and want to experiment with image upscaling.
- You can evaluate and maintain the code yourself under the AGPL-3.0 license.
- You want to compare a self-run workflow with the separately hosted ClarityAI service.
Look elsewhere if
- You need a project with recent maintenance, releases, or demonstrated issue and pull request handling.
- You need open-source Flux upscaling, which the README says is only available through the author's app and API.
- You need an easy hosted workflow and do not want to configure Cog or a Stable Diffusion interface.
All health signals
| Last commit | 2025-03-06 (1.7 years ago) |
|---|---|
| Commits, last 90 days | 0 |
| Releases, last 12 months | 0 |
| Contributors | 4 (top contributor: 91% of commits) |
| Issues closed, last 90 days | 0 |
| Pull requests merged, last 90 days | 0 |
| Project age | 2 years |
Checked on 2026-11-02 with the GitHub API.
Project history
Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.
Stars
5,174Forks
532Change since Nov 11, 2026: 0 stars·0 forks
Overview
Clarity Upscaler is an AI image upscaler and enhancer, packaged as a Cog implementation and built around Stable Diffusion image-generation workflows. It aims to enlarge images while adding or refining detail, as a free, open-source alternative to paid image-enhancement services.
The repository is for people comfortable running model code or adapting Stable Diffusion workflows. The README also points to ComfyUI and AUTOMATIC1111 options; its Flux upscaling service is offered through ClarityAI.co and is explicitly not open source.
Key Features
- Upscale images through a Cog prediction interface.
- Supports multi-step upscaling and pre-downscaling, according to the project updates.
- Offers options for sharpening and pattern upscaling.
- Supports custom Safetensors checkpoints and LoRAs.
- Includes an anime upscaling workflow.
- Provides output in JPG, PNG, and WebP formats.
- Can be used through related ComfyUI workflows or an AUTOMATIC1111 tutorial.
Use Cases
- Image creators can enlarge generated images and add detail before sharing or printing.
- Stable Diffusion users can incorporate upscaling into existing ComfyUI or AUTOMATIC1111 workflows.
- Developers familiar with Cog can run the prediction implementation or adapt it for an image-processing application.
- Anime artists can try the project's anime-oriented upscaling workflow.
What you need
Detected in the repository
- Node.js (from package.json)
- Python (from pyproject.toml)
- A test suite
License in plain words
AGPL-3.0network copyleft
- Commercial use: yes
- Modify and redistribute: yes
- You must keep: the license notice
- Share your changes: yes, the full source, also when people only use it over a network (e.g. as a hosted service)
- Includes an explicit patent grant from the contributors:
A summary, not legal advice: the LICENSE file is what applies.
Getting Started
Install and configure Cog, then run the repository's weight download script and make a prediction:
python download_weights.py
cog predict -i image="link-to-image"
See the README for Cog setup details and instructions for other workflows.
Alternatives
- upscayl: Upscayl is a cross-platform desktop app focused on AI image enlargement, while Clarity Upscaler uses Stable Diffusion workflows and Cog.
| Project | Language | License | Stars | Status |
|---|---|---|---|---|
| clarity-upscaler | Python | AGPL-3.0 | 5.2k | Inactive |
| upscayl | TypeScript | AGPL-3.0 | 50.1k | Quiet |
Considerations
The project is marked inactive: it has had no commits in over a year and no releases in the past year. Most of the code comes from one person, and there has been no recent issue or pull request activity in the measured period. This increases the risk of having to troubleshoot or maintain the implementation yourself.
The README describes a Cog-based implementation and points to Stable Diffusion interfaces, so running it involves model and workflow setup rather than a turnkey hosted experience. The supplied requirements data lists Node.js and Python, but does not indicate Docker or CI configuration. The AGPL-3.0 license also matters if you modify or distribute the code or make it available as part of a network service. Finally, Flux upscaling is not part of the open-source repository.
Found this useful?
Share it with someone who would like clarity-upscaler.