instructir-GGUF / README.md
cstr's picture
Add model card
75a28fe verified
|
Raw
History Blame Contribute Delete
569 Bytes
---
license: mit
tags: [gguf, image-restoration, instructir, all-in-one, text-guided]
pipeline_tag: image-to-image
---
# InstructIR All-in-One Restoration (GGUF)
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](https://github.com/mv-lab/InstructIR) (MIT, ECCV 2024).