test model
- proof of concept (not for production)
- x-image is able to run in 4-8 steps and has same structure of z-image (interchangeable)
- opt to use pig-clip + adapter for text encoder instead of qwen3-4b (though both works)
call ggk internal diffuser engine from CLI straight
ggk diffuser engine -- --diffusion-model x_image-nvfp4.gguf --vae pig_flux_vae_fp32-f16.gguf --llm pig_clip-nvfp4.gguf --llm-adapter pig_qwen3_4b_adapter-f16.gguf -p "cute anime style girl with pinky messy long hair blue eyes wearing a maid outfit with a long black gold leaf pattern dress and a white apron, it is a postcard held by a hand in front of a beautiful realistic city at sunset and there is cursive writing that says GGUF" --cfg-scale 1.0 --steps 8 --offload-to-cpu --diffusion-fa -v -o out.png
for GUI panel (powered by gk)
ggk
or run it with gguf-conncetor
ggc gk