Post

crispz-krea2 is a Fooocus-style web studio for Krea 2, the open-weights successor of FLUX.1 Krea, wrapped in the same workbench as crispz-studio. Everything runs on your own GPU, no ComfyUI, no cloud.

• Text to Image with styles, wildcards, tag autocomplete, prompt variants, live preview and Stop; Upscale after generate chains each image through ESRGAN.
• Models: single-file checkpoints from CivitAI, LoRAs with hot swap, a CivitAI search with previews and trigger words.
• Job queue and X/Y/Z grids for overnight batches and side-by-side comparisons.
• Prompt AI, local: Describe, Improve and Vision Mix through Ollama; Remove BG, Face Swap, CLI and the family protocol v1.
• What it does not do, said plainly: diffusers has no Krea 2 img2img pipeline yet, so the upscale is a pure ESRGAN enlargement and there is no Vary, no inpaint. For those, send the image to another crispz studio (klein, flux3, studio).

Hardware: an NVIDIA GPU; 16 GB of VRAM is comfortable with offload. Check the Krea 2 model card on Hugging Face for its licence and token requirement.

Pinokio launcher: https://github.com/mikecastrodemaria/crispz-krea2.pinokio
Source: https://github.com/mikecastrodemaria/crispz-krea2

Install (Pinokio)

1. In Pinokio, open Discover and paste https://github.com/mikecastrodemaria/crispz-krea2.pinokio.
2. Click Install: the launcher clones the app, creates the venv, installs the requirements and PyTorch (CUDA 12.8 on NVIDIA).
3. Click Start, then Open Web UI. The first render downloads the model.