ggk diffuser engine -- --diffusion-model iris-3b-nvfp4.gguf --llm pig_clip-f16.gguf --llm-adapter pig_qwen3vl_layerwise_adapter-f16.gguf -p "a lovely pig in sunglasses" --cfg-scale 3 -H 1024 -W 1024 --diffusion-fa -o out.png

use the full LLM (simple)

ggk --diffusion-model iris-3b-nvfp4.gguf --llm qwen3vl-4b-it-q4_k_m.gguf -p "a lovely pig in sunglasses" --cfg-scale 3 -H 1024 -W 1024 --diffusion-fa -o out.png

use adapter (simple)

ggk --diffusion-model iris-3b-nvfp4.gguf --llm pig_clip-f16.gguf --llm-adapter pig_qwen3vl_layerwise_adapter-f16.gguf -p "a lovely pig in sunglasses" --steps 15 --cfg-scale 3 -H 1024 -W 1024 --diffusion-fa -o out.png

*if not specify will route to diffuser/diffusion engine by default now

Downloads last month: 861

GGUF

Model size

3B params

Architecture

pig

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for gguf-org/iris-3b-gguf

Base model

speridlabs/iris-3b

Quantized

(7)

this model