ali-vilab/FreeScale
[ICCV 2025] Code for FreeScale, a tuning-free method for higher-resolution visual generation
This tool helps digital artists, graphic designers, and content creators produce incredibly high-resolution images, up to 8K, from text descriptions or existing lower-resolution images. It takes your text prompt or an initial image and generates a much sharper, more detailed visual without needing complex adjustments. If you're creating visuals for large displays, print, or detailed digital art, this is designed for you.
149 stars. No commits in the last 6 months.
Use this if you need to generate extremely high-resolution images (like 4K or 8K) from text prompts or enhance existing images, especially when using Stable Diffusion XL models.
Not ideal if your primary goal is fast, lower-resolution image generation where minor quality differences are acceptable, or if you don't have access to powerful computing resources.
Stars
149
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 09, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ali-vilab/FreeScale"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cswry/SeeSR
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
JJLibra/SALAD-Pan
🤗 Official implementation for "SALAD-Pan: Sensor-Agnostic Latent Adaptive Diffusion for...
open-mmlab/mmgeneration
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
Janspiry/Image-Super-Resolution-via-Iterative-Refinement
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
hanjq17/Spectrum
[CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration