Can You Upscale a Malfoid AI Portrait for a Poster? Lanczos vs FSRCNN vs Nearest, Measured With a Round-Trip Test

pip install opencv-contrib-python-headless numpy mkdir models curl -L -o models/FSRCNN_x2.pb https://raw.githubusercontent.com/Saafke/FSRCNN_Tensorflow/master/models/FSRCNN_x2.pb curl -L -o models/FSRCNN_x4.pb https://raw.githubusercontent.com/Saafke/FSRCNN_Tensorflow/master/models/FSRCNN_x4.pb 

#!/usr/bin/env python3 """Compare ways to enlarge a 1K portrait, with numbers instead of eyeballing. Round-trip test: shrink the picture 2x (or 4x), enlarge it back with each method, and score the result against the original (PSNR and SSIM on luma, plus a ringing score around hard edges). The method that rebuilds the original best is the one to use for a real 2x/4x enlargement. pip install opencv-contrib-python-headless numpy python upscale_compare.py portrait.png [--scale 2] [--models DIR] [--out DIR] [--sheet sheet.png] --models DIR is optional; put FSRCNN_x2.pb / FSRCNN_x4.pb there (from github.com/Saafke/FSRCNN_Tensorflow/tree/master/models) to include the small learned upscaler. Without it only the classic filters run. """ import argparse, os, sys import cv2 import numpy as np def luma(img): return cv2.cvtColor(img, cv2.COLOR_BGR2YCrCb)[:, :, 0].astype(np.float64) def psnr(a, b): mse = np.mean((luma(a) - luma(b)) ** 2) return float("inf") if mse == 0 else 10 * np.log10(255.0 ** 2 / mse) def ssim(a, b): x, y = luma(a), luma(b) c1, c2 = (0.01 * 255) ** 2, (0.03 * 255) ** 2 blur = lambda z: cv2.GaussianBlur(z, (11, 11), 1.5) mx, my = blur(x), blur(y) sxx, syy, sxy = blur(x * x) - mx * mx, blur(y * y) - my * my, blur(x * y) - mx * my m = ((2 * mx * my + c1) * (2 * sxy + c2)) / ((mx * mx + my * my + c1) * (sxx + syy + c2)) return float(m.mean()) def ringing(ref, out): """Mean overshoot (in 8-bit levels) next to strong edges of the reference.""" e = cv2.Canny(ref, 80, 160) > 0 band = cv2.dilate(e.astype(np.uint8), np.ones((5, 5), np.uint8)) > 0 band &= ~e lo = cv2.erode(luma(ref), np.ones((5, 5))) hi = cv2.dilate(luma(ref), np.ones((5, 5))) y = luma(out) over = np.maximum(y - hi, 0) + np.maximum(lo - y, 0) return float(over[band].mean()) if band.any() else 0.0 def unsharp(img, amount=0.6, sigma=1.0): blur = cv2.GaussianBlur(img, (0, 0), sigma) return cv2.addWeighted(img, 1 + amount, blur, -amount, 0) def methods(scale, models): m = { "nearest": lambda im: cv2.resize(im, None, fx=scale, fy=scale, interpolation=cv2.INTER_NEAREST), "bilinear": lambda im: cv2.resize(im, None, fx=scale, fy=scale, interpolation=cv2.INTER_LINEAR), "bicubic": lambda im: cv2.resize(im, None, fx=scale, fy=scale, interpolation=cv2.INTER_CUBIC), "lanczos4": lambda im: cv2.resize(im, None, fx=scale, fy=scale, interpolation=cv2.INTER_LANCZOS4), "lanczos4+unsharp": lambda im: unsharp(cv2.resize(im, None, fx=scale, fy=scale, interpolation=cv2.INTER_LANCZOS4)), } path = os.path.join(models, f"FSRCNN_x{scale}.pb") if models else "" if path and os.path.exists(path): sr = cv2.dnn_superres.DnnSuperResImpl_create() sr.readModel(path) sr.setModel("fsrcnn", scale) m["fsrcnn"] = sr.upsample elif models: print(f"note: {path} not found, skipping FSRCNN", file=sys.stderr) return m def main(): ap = argparse.ArgumentParser() ap.add_argument("image") ap.add_argument("--scale", type=int, default=2, choices=[2, 4]) ap.add_argument("--models", default="") ap.add_argument("--out", default="") ap.add_argument("--sheet", default="", help="write a labelled crop sheet (PNG) to look at") ap.add_argument("--crop", default="0.35,0.30,0.30,0.20", help="sheet crop as x,y,w,h fractions of the image (default: around the eyes)") a = ap.parse_args() ref = cv2.imread(a.image, cv2.IMREAD_COLOR) if ref is None: sys.exit(f"cannot read {a.image}") h, w = ref.shape[:2] h, w = h - h % a.scale, w - w % a.scale ref = ref[:h, :w] small = cv2.resize(ref, (w // a.scale, h // a.scale), interpolation=cv2.INTER_AREA) print(f"{a.image}: {w}x{h}, round trip via {w // a.scale}x{h // a.scale} (x{a.scale})") print(f"{'method':<18}{'PSNR dB':>9}{'SSIM':>8}{'ringing':>9}") ms = methods(a.scale, a.models) rows, ups = [], {} for name, f in ms.items(): up = f(small)[:h, :w] ups[name] = up rows.append((name, psnr(ref, up), ssim(ref, up), ringing(ref, up))) for name, p, s, r in sorted(rows, key=lambda t: -t[2]): print(f"{name:<18}{p:>9.2f}{s:>8.4f}{r:>9.2f}") # Nearest-neighbour can top SSIM on fine random texture (it keeps local  # contrast), but it prints as visible blocks, so it never gets auto-picked.  best = max((r for r in rows if r[0] != "nearest"), key=lambda t: t[2])[0] print(f"best by SSIM (excluding nearest): {best}") if a.sheet: fx, fy, fw, fh = (float(v) for v in a.crop.split(",")) x0, y0, cw, ch = int(fx * w), int(fy * h), int(fw * w), int(fh * h) tiles = [] for name in ["original"] + [r[0] for r in rows]: src = ref if name == "original" else ups[name] t = cv2.resize(src[y0:y0 + ch, x0:x0 + cw], (cw * 2, ch * 2), interpolation=cv2.INTER_NEAREST) t = cv2.copyMakeBorder(t, 28, 4, 4, 4, cv2.BORDER_CONSTANT, value=(255, 255, 255)) cv2.putText(t, name, (6, 21), cv2.FONT_HERSHEY_SIMPLEX, 0.6, (0, 0, 0), 1, cv2.LINE_AA) tiles.append(t) while len(tiles) % 3: tiles.append(np.full_like(tiles[0], 255)) grid = np.vstack([np.hstack(tiles[i:i + 3]) for i in range(0, len(tiles), 3)]) cv2.imwrite(a.sheet, grid) print(f"wrote {a.sheet} (crop shown at 2x with nearest, so you see pixels)") if a.out: os.makedirs(a.out, exist_ok=True) full = ms[best](cv2.imread(a.image, cv2.IMREAD_COLOR)) p = os.path.join(a.out, f"x{a.scale}-{best}.png") cv2.imwrite(p, full) H, W = full.shape[:2] print(f"wrote {p} {W}x{H}; at 300 ppi that prints {W / 300 * 2.54:.1f} x {H / 300 * 2.54:.1f} cm") if __name__ == "__main__": main() 

#!/usr/bin/env python3 """Draw a synthetic 3:4 'Malfoid-style' test portrait (no real face, no AI). Shapes only: dark corridor, candle glow, platinum hair, an oval face, white shirt, green-and-silver striped tie, dark robe. --texture adds thin hair strands and fabric grain, so resampling and line-art scripts have some fine detail to chew on. No real face, no AI, nobody's photo. python make_test_portrait.py out.png [--seed 1] [--size 768x1024] [--texture] """ import argparse import random from PIL import Image, ImageDraw, ImageFilter def face(d, s, fw, skin): d.ellipse([int((264 - fw) * s), int(250 * s), int((504 + fw) * s), int(560 * s)], fill=skin) # face  for ex in (330, 438): # eyes  d.ellipse([int((ex - 16) * s), int(380 * s), int((ex + 16) * s), int(398 * s)], fill=(250, 250, 250)) d.ellipse([int((ex - 7) * s), int(382 * s), int((ex + 7) * s), int(396 * s)], fill=(110, 130, 120)) dSource：https://dev.to/lpgit/can-you-upscale-a-malfoid-ai-portrait-for-a-poster-lanczos-vs-fsrcnn-vs-nearest-measured-with-a-3nih
My favorites