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
Downloads last month
66
GGUF
Model size
621k params
Architecture
esrgan
Hardware compatibility
Log In to add your hardware

32-bit

Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support