GGUF

🐷pig architecture gguf clip

  • natively trained multipurpose clip for gk engine
  • low vram alternative/substitute of t5xxl
  • 85% smaller and more cost effective

how it works

simply replace --t5xxl t5xxl.gguf with --llm pig_clip-nvfp4.gguf --llm-adapter pig_t5_adapter-f16.gguf

examples

test it with pixart

ggk diffuser engine -- --diffusion-model pixart-nvfp4.gguf --vae pig_pixart_vae_fp16-f16.gguf --llm pig_clip-nvfp4.gguf --llm-adapter pig_t5_adapter-f16.gguf -p "close-up portrait of dog" --diffusion-fa -v -o out.png

test it with sd-lite

ggk diffuser engine -- --diffusion-model model.gguf --vae vae.gguf --clip_l clip_l.gguf --clip_g clip_g.gguf --llm pig_clip-nvfp4.gguf --llm-adapter pig_t5_adapter-f16.gguf -p "close-up portrait of dog" --steps 8 --cfg-scale 1 --sampling-method euler --clip-on-cpu --diffusion-fa -v -o out.png

screenshot

Reference

pig engine - the new gguf compute kernels (gk)

Downloads last month
115
GGUF
Model size
0.6B params
Architecture
pig
Hardware compatibility
Log In to add your hardware

4-bit

16-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support