city96/SD-Latent-Upscaler

Upscaling stable diffusion latents using a small neural network.

38
/ 100
Emerging

This tool helps AI artists and graphic designers enhance the resolution of their Stable Diffusion-generated images without losing quality or introducing unwanted changes. You feed it a low-resolution latent image (the intermediate representation before final pixel conversion), and it outputs a higher-resolution latent image. This allows you to generate larger, more detailed images from your prompts.

168 stars. No commits in the last 6 months.

Use this if you need to upscale your AI-generated images, particularly from Stable Diffusion, and want to maintain image integrity and avoid common artifacts associated with direct upscaling.

Not ideal if you are looking for an upscaling solution for Auto1111 workflows, as it is not currently supported, or if you need an upscaler for non-Stable Diffusion images.

AI-art image-generation digital-art graphic-design image-enhancement
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

168

Forks

13

Language

Python

License

Apache-2.0

Category

controlnet-tools

Last pushed

May 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/city96/SD-Latent-Upscaler"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.