Downloads · 30 days
0
naksyu/lunasr-general-mc65-ww35-x2
lunasr-general-mc65-ww35-x2 is a image-to-image model from naksyu. Use it when you need one image transformed into another. It is set up for pytorch. The card lists the license as mit.
Tiny x2 luminance super-resolution model specialized for captured game footage. The training patch mixture used approximately 65% Minecraft frames and 35% Wuthering Waves frames.
Downloads · 30 days
0
Access
Public
Updated Jul 26, 2026
Repo size
106 KB
Likes
0
Public
Click a slice to open those files.
.pt64.3 KB · 43%
From the Hugging Face model README
Tiny x2 luminance super-resolution model specialized for captured game footage. The training patch mixture used approximately 65% Minecraft frames and 35% Wuthering Waves frames.
contains no source videos, extracted frames, faces, or training dataset.
pytorch_model.ptmodel.onnxThe ONNX graph accepts [1, 1, 540, 960] float32 luma and returns [1, 1, 1080, 1920] float32 residual. Compose the final image as:
rgb_hr = clamp(bilinear_x2(rgb_lr) + luma_residual, 0, 1)
The same residual is added to R, G, and B to preserve the bilinearly upscaled chroma.
python -m pip install -r requirements.txt
python -m scripts.upscale_images `
--input "input.png" `
--output "output" `
--checkpoint pytorch_model.pt `
--device cuda `
--save-bilinear
Video upscaling requires FFmpeg and FFprobe on PATH:
python scripts/upscale_video.py `
--input "input.mp4" `
--output "output.mp4" `
--checkpoint pytorch_model.pt `
--device cuda `
--batch-size 16
If the source container reports incorrect FPS metadata, normalize the input timestamps first or correct the output timestamps afterward.
BT.709 luma PSNR improvement over bilinear x2:
| Domain | Baseline | Model | Delta |
|---|---|---|---|
| Minecraft | 40.369 dB | 42.566 dB | +2.197 dB |
| Wuthering Waves | 46.005 dB | 47.874 dB | +1.869 dB |
The 65:35 weighted delta was +2.082 dB. See metrics/model_domain_eval_matrix.json for the reproducible evaluation record.
3.8743019104e-7Add, Conv, DepthToSpace, ReluRTX 4060 Ti FP32 measurements for the CUDA-resident RGB composition path:
| Input -> output | Batch 1 throughput |
|---|---|
| 256x256 -> 512x512 | about 1,148 fps |
| 512x512 -> 1024x1024 | about 534 fps |
These are implementation-specific local measurements, not guaranteed device performance.
model.onnx: fixed 960x540 residual-only ONNXmodel.json: deployment contractmodel.verification.json: numerical verificationpytorch_model.pt: original training checkpointlunasr/model.py: architecture definitionscripts/: image, video, export, and CUDA benchmark utilitiesSHA256SUMS.txt: file integrity manifest