|
|
--- |
|
|
license: openrail++ |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- PixArt-alpha/PixArt-XL-2-1024-MS |
|
|
pipeline_tag: text-to-image |
|
|
tags: |
|
|
- pixart |
|
|
- gguf-node |
|
|
widget: |
|
|
- text: close-up portrait of girl |
|
|
output: |
|
|
url: samples\ComfyUI_00001_.png |
|
|
- text: close-up portrait of cat |
|
|
output: |
|
|
url: samples\ComfyUI_00002_.png |
|
|
- text: close-up portrait of young lady |
|
|
output: |
|
|
url: samples\ComfyUI_00003_.png |
|
|
- text: close-up portrait of girl |
|
|
output: |
|
|
url: samples\ComfyUI_00005_.png |
|
|
- text: close-up portrait of young lady |
|
|
output: |
|
|
url: samples\ComfyUI_00004_.png |
|
|
- text: close-up portrait of girl |
|
|
output: |
|
|
url: samples\ComfyUI_00006_.png |
|
|
--- |
|
|
|
|
|
# **gguf quantized version of pixart** |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
## **setup (once)** |
|
|
- drag pixart-xl-2-1024-ms-q4_k_m.gguf [[1GB](https://huggingface.co/calcuis/pixart/blob/main/pixart-xl-2-1024-ms-q4_k_m.gguf)] to > ./ComfyUI/models/diffusion_models |
|
|
- drag t5xxl_fp16-q4_0.gguf [[2.9GB](https://huggingface.co/calcuis/pixart/blob/main/t5xxl_fp16-q4_0.gguf)] to > ./ComfyUI/models/text_encoders |
|
|
- drag pixart_vae_fp8_e4m3fn.safetensors [[83.7MB](https://huggingface.co/calcuis/pixart/blob/main/pixart_vae_fp8_e4m3fn.safetensors)] to > ./ComfyUI/models/vae |
|
|
|
|
|
## **run it straight (no installation needed way)** |
|
|
- run the .bat file in the main directory (assuming you are using the gguf-node [pack](https://github.com/calcuis/gguf/releases) below) |
|
|
- drag the workflow json file (below) or the demo picture above to > your browser |
|
|
|
|
|
### **workflow** |
|
|
- example workflow for [gguf](https://huggingface.co/calcuis/pixart/blob/main/workflow-pixart-gguf.json) |
|
|
- example workflow for [safetensors](https://huggingface.co/calcuis/pixart/blob/main/workflow-pixart-safetensors.json) |
|
|
|
|
|
### review |
|
|
- should set the output image size according to the model stated, i.e., 1024x1024 or 512x512 |
|
|
- pixart-xl-2-1024-ms is recommended (with 1024x1024 size) |
|
|
- small size model but good quality pictures; and t5 encoder allows you inputting short description or sentence instead of tag(s) |
|
|
- more quantized versions of t5xxl encoder can be found [here](https://huggingface.co/chatpig/t5xxl/tree/main) |
|
|
- upgrade your gguf-node (see the last item in reference list below) to the latest version for pixart model support |
|
|
|
|
|
### **paper** |
|
|
- [pixart-α](https://arxiv.org/pdf/2310.00426) |
|
|
- [pixart-Σ](https://arxiv.org/pdf/2403.04692) |
|
|
- [high-resolution image synthesis](https://arxiv.org/pdf/2112.10752) |
|
|
|
|
|
### **reference** |
|
|
- base model from [pixart-alpha](https://huggingface.co/PixArt-alpha) |
|
|
- comfyui [comfyanonymous](https://github.com/comfyanonymous/ComfyUI) |
|
|
- gguf-node ([pypi](https://pypi.org/project/gguf-node)|[repo](https://github.com/calcuis/gguf)|[pack](https://github.com/calcuis/gguf/releases)) |
