license: mit
library_name: diffusers
stage-a-ft-hq
stage-a-ft-hq is a version of Würstchen's Stage A that was finetuned to generate sharper details and textures.
stage-a-ft-hq works with any Würstchen-derived model (including Stable Cascade).
TODO: comparison goes here
🧨 Diffusers Usage
# TODO: code goes here
Explanation
Image generators like Würstchen and Stable Cascade create images via a multi-stage process. Stage A is the ultimate stage, responsible for rendering out full-resolution human-interpretable images.
The original Stage A tends to render smoothed-out textures with a distinctive grain pattern on top.
stage-a-ft-hq was finetuned on a high-quality dataset in order to generate cleaner, sharper, more realistic textures with fewer distinctive artifacts.
Recommended Settings
To generate highly detailed images, you probably want to use stage-a-ft-hq (which improves very fine detail) in combination with a large Stage B step count (which improves mid-level detail).