GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

gguf-org/pixart-gguf overview

test model proof of concept not for production get either t5xxl https://huggingface.co/gguf org/diffusion/blob/main/t5xxl.gguf or pig clip https://huggingface.…

gguflicense:mitregion:us

Runs locally from ~159.7 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
149
Likes
1
Pipeline
Author

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
pig_pixart_vae_fp16-f16.ggufGGUFF16159.7 MBDownload
pixart-nvfp4.ggufGGUFGGUF351.9 MBDownload

Model Details

Model IDgguf-org/pixart-gguf
Authorgguf-org
Pipeline
Licensemit
Base model
Last modified2026-08-22T16:30:50.000Z

Model README

---

license: mit

widget:

  • text: >-

close-up portrait of dog

output:

url: out2.png

  • text: >-

close-up portrait of young lady

output:

url: out1.png

  • text: >-

close-up portrait of girl

output:

url: out3.png

---

test model

  • proof of concept (not for production)
  • get either t5xxl or pig-clip as text encoder

<Gallery />

call ggk internal diffuser engine from CLI straight

ggk diffuser engine -- --diffusion-model pixart-nvfp4.gguf --vae pig_pixart_vae_fp16-f16.gguf --t5xxl t5xxl.gguf -p "close-up portrait of girl" --diffusion-fa -v -o out.png

for GUI panel (powered by gk)

ggk

or run it with gguf-conncetor

ggc gk

!screenshot

Reference

pig engine - the new gguf compute kernels (gk)

Run gguf-org/pixart-gguf with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models