Add image perspective editing and related tools

- Implemented the Image Perspective tool for editing image corners in Blender.
- Created a new operator `EditImagePerspective` to handle the perspective transformation.
- Added a preview feature for the perspective adjustment.
- Introduced the `ImagePolylineTool` for editing image masks with polylines.
- Developed backend support for Real-ESRGAN model inference, including ONNX integration.
- Added functionality for image masking and background removal.
- Created unit tests for the Real-ESRGAN ONNX model to ensure correct preprocessing and inference.

src/anyimage/server/jobs/debug_realesrgan.py

@@ -0,0 +1,26 @@
+from ..media import copy_frames
+from ..models.realesrgan import infer_one
+from .common import input_frames
+
+
+def run(context, parameters):
+    context.progress(0.02, "Preparing Real-ESRGAN API input")
+    context.directory.mkdir(parents=True, exist_ok=True)
+    with input_frames(context, parameters) as images:
+        for index, image in enumerate(images):
+            context.check_cancelled()
+            prediction = infer_one(
+                context.resource("model_manager"),
+                parameters,
+                image,
+            )
+            suffix = "" if len(images) == 1 else f".{index + 1:04d}"
+            prediction.save(
+                context.directory / f"prediction{suffix}.png",
+                format="PNG",
+                compress_level=1,
+            )
+        copy_frames(images, context.directory)
+    context.check_cancelled()
+    context.progress(1.0, "Saved raw Real-ESRGAN API prediction")
+    return {"directory": "."}

src/anyimage/server/jobs/image_mask.py

@@ -67,13 +67,11 @@ def apply_selection_mask(foreground, selection_mask):
     return Image.fromarray(pixels, mode="RGBA")
 
 
-def crop_to_alpha(image, bounds, padding=0):
-    """Crop an RGBA image to nonzero Alpha and expand it by pixel padding."""
+def crop_to_alpha(image, bounds):
+    """Crop an RGBA mask image to its nonzero Alpha bounds."""
     import numpy as np
     from PIL import Image
 
-    if padding < 0:
-        raise ValueError("Padding must not be negative")
     pixels = np.asarray(image.convert("RGBA"), dtype=np.uint8)
     visible_y, visible_x = np.nonzero(pixels[:, :, 3] > 0)
     if not len(visible_x):
@@ -85,23 +83,23 @@ def crop_to_alpha(image, bounds, padding=0):
     output = Image.new(
         "RGBA",
         (
-            content_right - content_left + padding * 2,
-            content_bottom - content_top + padding * 2,
+            content_right - content_left,
+            content_bottom - content_top,
         ),
         (0, 0, 0, 0),
     )
-    output.paste(image, (padding - content_left, padding - content_top))
+    output.paste(image, (-content_left, -content_top))
     left, top, _right, _bottom = bounds
     return output, (
-        left + content_left - padding,
-        top + content_top - padding,
-        left + content_right + padding,
-        top + content_bottom + padding,
+        left + content_left,
+        top + content_top,
+        left + content_right,
+        top + content_bottom,
     )
 
 
 def run(context, parameters):
-    """Remove the background from an image selection and return source bounds."""
+    """Refine a gesture mask with BEN2 and return its source-image bounds."""
     started = time.perf_counter()
     context.progress(0.05, "Preparing image selection")
     context.check_cancelled()
@@ -124,15 +122,13 @@ def run(context, parameters):
     context.check_cancelled()
     context.progress(0.9, "Applying selection mask")
     output, bounds = crop_to_alpha(
-        apply_selection_mask(foreground, selection_mask),
-        bounds,
-        int(parameters.get("padding", 0)),
+        apply_selection_mask(foreground, selection_mask), bounds
     )
     output_path = output_directory / "image.png"
     output.save(output_path, format="PNG", compress_level=1)
     bounds_path = output_directory / "bounds.json"
     bounds_path.write_text(json.dumps(bounds, separators=(",", ":")), encoding="utf-8")
     elapsed_ms = (time.perf_counter() - started) * 1000.0
-    message = f"Image background removal finished in {elapsed_ms:.0f} ms"
+    message = f"Image selection refined in {elapsed_ms:.0f} ms"
     context.progress(1.0, message)
     return {"image": output_path.name, "bounds": bounds_path.name}