cstr/instructir-GGUF

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 (MIT, ECCV 2024).

Provenance and EU AI Act Art. 53 note

• Upstream model: mv-lab/InstructIR.
• Upstream licence: mit. This repository redistributes under the same terms; it grants no rights the upstream licence does not.
• What was done here: format conversion and/or quantisation only (GGUF). No training, no fine-tuning, no merging, no distillation, no change to architecture, vocabulary or capability. Only the numeric representation of the upstream weights differs.
• Training data: documented — where it is documented at all — by the upstream provider; see the upstream model card. No training data was used, added or selected by this repository.
• Provider status: under Regulation (EU) 2024/1689 the upstream authors remain the provider of this model. Converting the serialisation format does not make this repository the provider of a new general-purpose AI model, and no such claim is made. Questions about training content, copyright policy or model capability belong upstream.