Text-guided NAFNet U-Net for 7 restoration tasks: denoise, deblur,
dehaze, derain, super-resolution, low-light enhancement, general
enhancement. 16M params, 61 MB F32.
Pre-computed task embeddings baked into GGUF — no text encoder at runtime.
Select task by integer ID (0-6).
Parity: cos=1.000000 vs Python reference.
Source:
mv-lab/InstructIR (MIT, ECCV 2024).
