Pixart

🚀 gguf quantized version of pixart

This project offers a gguf quantized version of PixArt, enabling users to generate high - quality text - to - image results. It simplifies the setup process and provides various workflow examples for different usage scenarios.

🚀 Quick Start

Setup (Once)

• Drag pixart-xl-2-1024-ms-q4_k_m.gguf [1GB] to ./ComfyUI/models/diffusion_models.
• Drag t5xxl_fp16-q4_0.gguf [2.9GB] to ./ComfyUI/models/text_encoders.
• Drag pixart_vae_fp8_e4m3fn.safetensors [83.7MB] 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 below).
• Drag the workflow json file (below) or the demo picture above to your browser.

Workflow

• Example workflow for gguf.
• Example workflow for safetensors.

📚 Documentation

Review

• Should set the output image size according to the model stated, i.e., 1024x1024 or 512x512.
• pixart-xl-2-1024-ms and pixart-sigma-xl-2-1024-ms are recommended (with 1024x1024 size).
• Small size model but good quality pictures; and the T5 encoder allows you to input a short description or sentence instead of tag(s).
• More quantized versions of the T5XXL encoder can be found here.
• Upgrade your gguf - node (see the last item in the reference list below) to the latest version for PixArt model support.

Paper

• pixart - α
• pixart - Σ
• high - resolution image synthesis

Reference

• Base model from [pixart - alpha](https://huggingface.co/PixArt - alpha).
• ComfyUI comfyanonymous.
• gguf - node ([pypi](https://pypi.org/project/gguf - node)|repo|pack)

📄 License

The project uses the OpenRail++ license.

📦 Information Table

🖼️ Widget Examples

Example 1

• Text: a close - up shot of a beautiful girl in a serene world. She has white hair and is blindfolded, with a calm expression. Her hands are pressed together in a prayer pose, with fingers interlaced and palms touching. The background is softly blurred, enhancing her ethereal presence.
• Parameters:
  • Negative Prompt: blurry, cropped, ugly
• Output: samples\ComfyUI_00007_.png

Example 2

• Text: a wizard with a glowing staff and a glowing hat, colorful magic, dramatic atmosphere, sharp focus, highly detailed, cinematic, original composition, fine detail, intricate, elegant, creative, color spread, shiny, amazing, symmetry, illuminated, inspired, pretty, attractive, artistic, dynamic background, relaxed, professional, extremely inspirational, beautiful, determined, cute, adorable, best
• Parameters:
  • Negative Prompt: blurry, cropped, ugly
• Output: samples\ComfyUI_00008_.png

Example 3

• Text: a girl stands amidst scattered glass shards, surrounded by a beautifully crafted and expansive world. The scene is depicted from a dynamic angle, emphasizing her determined expression. The background features vast landscapes with floating crystals and soft, glowing lights that create a mystical and grand atmosphere.
• Parameters:
  • Negative Prompt: blurry, cropped, ugly
• Output: samples\ComfyUI_00009_.png

Example 4

• Text: close - up portrait of girl
• Output: samples\ComfyUI_00001_.png

Example 5

• Text: close - up portrait of cat
• Output: samples\ComfyUI_00002_.png

Example 6

• Text: close - up portrait of young lady
• Output: samples\ComfyUI_00003_.png