gguf quantized version of pixart

Prompt

close-up portrait of girl

Prompt

close-up portrait of cat

Prompt

close-up portrait of young lady

Prompt

close-up portrait of girl

Prompt

close-up portrait of young lady

Prompt

close-up portrait of girl

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

review

• should set the output image size according to the model stated, i.e., 1024x1024 or 512x512
• small size model but good quality pictures; support image-to-image, image-text-to-image; and t5 encoder allows you to input short description or sentence instead of tag(s)
• upgrade your gguf-node to the latest version for pixart model support

reference

• base model from pixart-alpha
• comfyui comfyanonymous
• gguf-node (pypi|repo|pack)