crispz does one thing: it enlarges an image and puts real detail back into it, 100% local, no ComfyUI, no SwarmUI, no cloud. Two stages:
- Real-ESRGAN (through spandrel) for the true pixel enlargement, with overlap-add tiling and linear feathering: no visible seams, whole images up to 2048 px on a 5090, tiled above.
- Z-Image Turbo img2img at a low denoise, the pass that reinjects texture, skin, fabric and foliage without touching the composition.
You get a Gradio UI, a scriptable CLI and an interactive CLI with saved preferences, for one image or a whole folder. It is the upscaler that every crispz studio embeds; on its own it is the lightest way to finish renders made elsewhere.
Hardware: an NVIDIA GPU with 8 GB of VRAM or more. Z-Image Turbo is Apache 2.0, public on Hugging Face: no token.
Pinokio launcher: https://github.com/mikecastrodemaria/crispz.pinokio
Source: https://github.com/mikecastrodemaria/crispz
Install (Pinokio)
- In Pinokio, open Discover and paste
https://github.com/mikecastrodemaria/crispz.pinokio.
- Click Install: the launcher clones the app, creates the venv, installs the requirements and PyTorch for your GPU.
- Click Start, then Open Web UI. Drop an image, pick the ESRGAN model and the denoise, Upscale.
crispz does one thing: it enlarges an image and puts real detail back into it, 100% local, no ComfyUI, no SwarmUI, no cloud. Two stages:
You get a Gradio UI, a scriptable CLI and an interactive CLI with saved preferences, for one image or a whole folder. It is the upscaler that every crispz studio embeds; on its own it is the lightest way to finish renders made elsewhere.
Hardware: an NVIDIA GPU with 8 GB of VRAM or more. Z-Image Turbo is Apache 2.0, public on Hugging Face: no token.
Pinokio launcher: https://github.com/mikecastrodemaria/crispz.pinokio
Source: https://github.com/mikecastrodemaria/crispz
Install (Pinokio)
https://github.com/mikecastrodemaria/crispz.pinokio.