cstr/esrgan-sr-GGUF

Real-ESRGAN SRVGGNetCompact (GGUF)

4x image super-resolution via Real-ESRGAN SRVGGNetCompact (realesr-animevideov3). 620K params, 2.4 MB. 17 Conv3x3+PReLU layers + PixelShuffle(4) + global skip.

Parity: cos=1.000000 vs Python reference. Source: xinntao/Real-ESRGAN (BSD-3-Clause).

File	Size	Description
esrgan-x4-f32.gguf	2.4 MB	F32, 620K params, 4x upscale

Provenance and EU AI Act Art. 53 note

• Upstream model: xinntao/Real-ESRGAN.
• Upstream licence: bsd-3-clause. 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.