Pinokio
FeedAppsRemote
Download Pinokio
Sign inCreate accountJoin
Sign inCreate accountJoin

Post

Conversation

crispz-studio 1.16: a Z-Image Turbo creation and enhancement studio, local, 1-click

Mike Castro Demaria@supersoniquestudio·1h

crispz-studio on an RTX 5090

crispz-studio is a Fooocus-style web studio for Z-Image Turbo, the distilled 6B model that renders a clean 1024 image in about 8 steps at guidance 0. It is the root of the crispz family: the other studios (klein, krea, qwen-edit, flux3, moss, ideogram) are forks of this one, so what you learn here works everywhere. Everything runs on your own GPU, no ComfyUI, no cloud.

  • Text to Image with styles (277, searchable, with previews), wildcards, tag autocomplete, prompt variants, a live preview and Stop.
  • Upscale and enhance: Real-ESRGAN plus a Z-Image refine pass, tiled up to 4K, with one-click Vary (subtle / strong). Force aspect ratio can crop, or extend by generating the missing bands instead of cropping.
  • Models: single-file checkpoints from CivitAI, GGUF quants (Q3 to Q8, kept quantized in VRAM), FP8 and FP8-scaled files, LoRAs with hot swap, a CivitAI search with previews and trigger words.
  • Job queue and X/Y/Z grids: every setting snapshotted into a job, overnight batches, Pause and Stop that never lose a job, annotated contact sheets.
  • Prompt AI, local: Describe, Improve and Vision Mix through Ollama; Remove BG, Reframe / outpaint, Face Swap, a hand and face detailer.
  • boot_check: a smart diagnostic that tells you before the crash whether your torch build has kernels for your card (the classic RTX 50xx + wrong torch case), with the fix.
  • CLI and the family protocol v1 (czp): batch work, and the engine behind comics2crispz.

Hardware: an NVIDIA GPU; 8 GB of VRAM is enough with the GGUF quants and offload, more is comfortable. Z-Image Turbo is Apache 2.0, public on Hugging Face: no token.

Pinokio launcher: https://github.com/mikecastrodemaria/crispz-studio.pinokio
Source: https://github.com/mikecastrodemaria/crispz-studio

Install (Pinokio)

  1. In Pinokio, open Discover and paste https://github.com/mikecastrodemaria/crispz-studio.pinokio.
  2. Click Install: the launcher clones the app, creates the venv, installs the requirements and PyTorch (CUDA 12.8 on NVIDIA, ROCm / MPS / CPU elsewhere).
  3. Click Start, then Open Web UI. The first render downloads the model.
crispz-studiomikecastrodemaria/crispz-studio.pinokio
Loading conversation…

Replies

Post context

App used

crispz-studiomikecastrodemaria/crispz-studio.pinokio

Z-Image txt2img + upscaler/detailer studio (Fooocus-style, 100% local): txt2img, ESRGAN+Z-Image refine upscale, single-file/Civitai models, LoRA, s...

View app

Published by

@supersoniquestudio1h ago
Pinokio
PrivacyTerms
FeedAppsRemote

Post context

App used

crispz-studiomikecastrodemaria/crispz-studio.pinokio

Z-Image txt2img + upscaler/detailer studio (Fooocus-style, 100% local): txt2img, ESRGAN+Z-Image refine upscale, single-file/Civitai models, LoRA, s...

View app

Published by

@supersoniquestudio1h ago

Related posts

crispz-studio : a 100% local, Fooocus-style studio for Z-Image (no ComfyUI / SwarmUI)@mikecastrodemaria · 4mo agocrispz-moss 1.0.0: text in images that comes out exact, local, Apache 2.0@supersoniquestudio · 1h agoPotionUI 0.1.0 (beta) - LTX 2.5 Motion Transfer; MOSS-Image Inpaint; Exlirs and Editors in tabs@oroborus · 1d ago