From 9aaa53fe3221df04a9332f570bb843f0461409ff Mon Sep 17 00:00:00 2001
From: Victor Kuznetsov <kuznetsov.va@gmail.com>
Date: Thu, 28 May 2026 18:46:26 -0700
Subject: [PATCH] fix(metadata): preserve upload format and quality on strip

remove_ai_metadata now writes JPEG at quality 95 with 4:4:4 (no chroma
subsampling) instead of the lossy PIL defaults (q75, 4:2:0), and preserves
WebP losslessly instead of silently rewriting it as PNG.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
---
 src/remove_ai_watermarks/metadata.py | 12 +++++++++
 tests/test_metadata.py               | 38 ++++++++++++++++++++++++++++
 2 files changed, 50 insertions(+)

diff --git a/src/remove_ai_watermarks/metadata.py b/src/remove_ai_watermarks/metadata.py
index 4ea3c1c..9f678c3 100644
--- a/src/remove_ai_watermarks/metadata.py
+++ b/src/remove_ai_watermarks/metadata.py
@@ -695,8 +695,20 @@ def remove_ai_metadata(
         save_kwargs: dict[str, Any] = {}
         if fmt in (".jpg", ".jpeg"):
             save_kwargs["format"] = "JPEG"
+            # JPEG output is unavoidably lossy, so minimize the loss: high quality
+            # and no chroma subsampling (4:4:4). Without these PIL defaults to
+            # quality 75 + 4:2:0, which visibly degrades a re-saved image.
+            save_kwargs["quality"] = 95
+            save_kwargs["subsampling"] = 0
             if img.mode in ("RGBA", "P"):
                 img = img.convert("RGB")
+        elif fmt == ".webp":
+            # Preserve the WebP container losslessly instead of silently rewriting
+            # it as PNG (which changes the format and bloats the file).
+            save_kwargs["format"] = "WEBP"
+            save_kwargs["lossless"] = True
+            if img.mode == "P":  # WebP cannot encode palette mode
+                img = img.convert("RGBA" if "transparency" in img.info else "RGB")
         else:
             save_kwargs["format"] = "PNG"
 
diff --git a/tests/test_metadata.py b/tests/test_metadata.py
index b93fe0a..3e3c8b7 100644
--- a/tests/test_metadata.py
+++ b/tests/test_metadata.py
@@ -322,6 +322,44 @@ class TestRemoveAiMetadata:
         assert result == jpg_path
         assert jpg_path.exists()
 
+    def test_jpeg_output_is_high_quality(self, tmp_path):
+        """JPEG output uses high quality + 4:4:4 (no chroma subsampling), not the
+        lossy PIL defaults (quality 75, 4:2:0) that visibly degrade the image."""
+        from PIL.JpegImagePlugin import get_sampling
+
+        img = Image.new("RGB", (64, 64), color=(100, 150, 200))
+        png_path = tmp_path / "source.png"
+        img.save(png_path)
+
+        jpg_path = tmp_path / "output.jpg"
+        remove_ai_metadata(png_path, jpg_path)
+
+        with Image.open(jpg_path) as out:
+            assert get_sampling(out) == 0  # 4:4:4, no chroma subsampling
+            # quality 95 quantization tables stay well below the q75 defaults
+            # (whose max quant value is ~40+); q95 tops out around 12.
+            assert max(max(t) for t in out.quantization.values()) <= 15
+
+    def test_webp_output_preserves_format_losslessly(self, tmp_path):
+        """A .webp output keeps the WebP format (not silently rewritten to PNG)
+        and is pixel-identical to the source (lossless)."""
+        import numpy as np
+
+        rng = np.random.default_rng(0)
+        arr = rng.integers(0, 255, (48, 48, 3), dtype=np.uint8)
+        src = Image.fromarray(arr, "RGB")
+        pnginfo = PngInfo()
+        pnginfo.add_text("parameters", "ai stuff")
+        png_path = tmp_path / "source.png"
+        src.save(png_path, pnginfo=pnginfo)
+
+        webp_path = tmp_path / "output.webp"
+        remove_ai_metadata(png_path, webp_path)
+
+        with Image.open(webp_path) as out:
+            assert out.format == "WEBP"
+            assert np.array_equal(np.asarray(out.convert("RGB")), arr)
+
     def test_creates_parent_directories(self, tmp_path):
         img = Image.new("RGB", (32, 32))
         pnginfo = PngInfo()