1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
|
from __future__ import annotations
import argparse
import os
from collections import deque
from pathlib import Path
from PIL import Image
try:
from google import genai
except ImportError as exc: # pragma: no cover
raise SystemExit(
"Missing dependency: google-genai. Install it with "
r"'.\.venv\Scripts\python.exe -m pip install google-genai'."
) from exc
PROMPT = (
"Remove the entire background from this product photo and return only the product "
"on a fully transparent background as a PNG. Keep the full product intact, preserve "
"thin cable details, clean the inner loops and holes, and do not add any new objects "
"or shadows."
)
DEFAULT_CANVAS_SIZE = 1024
DEFAULT_TARGET_WIDTH = 820
DEFAULT_MIN_COMPONENT_PIXELS = 500
SUPPORTED_EXTENSIONS = {".jpg", ".jpeg", ".png", ".webp"}
def is_light_background_pixel(r: int, g: int, b: int) -> bool:
brightness = (r + g + b) / 3
spread = max(r, g, b) - min(r, g, b)
return brightness >= 170 and spread <= 35
def to_pil_image(image_obj) -> Image.Image:
if isinstance(image_obj, Image.Image):
return image_obj
pil_image = getattr(image_obj, "_pil_image", None)
if isinstance(pil_image, Image.Image):
return pil_image
as_pil = getattr(image_obj, "pil_image", None)
if isinstance(as_pil, Image.Image):
return as_pil
raise TypeError(f"Unsupported image object type: {type(image_obj)!r}")
def make_transparent_from_borders(image: Image.Image) -> Image.Image:
rgba = image.convert("RGBA")
width, height = rgba.size
pixels = rgba.load()
visited: set[tuple[int, int]] = set()
queue: deque[tuple[int, int]] = deque()
def push_if_bg(x: int, y: int) -> None:
if (x, y) in visited:
return
r, g, b, _ = pixels[x, y]
if is_light_background_pixel(r, g, b):
visited.add((x, y))
queue.append((x, y))
for x in range(width):
push_if_bg(x, 0)
push_if_bg(x, height - 1)
for y in range(height):
push_if_bg(0, y)
push_if_bg(width - 1, y)
while queue:
x, y = queue.popleft()
for nx, ny in ((x - 1, y), (x + 1, y), (x, y - 1), (x, y + 1)):
if 0 <= nx < width and 0 <= ny < height:
push_if_bg(nx, ny)
for x, y in visited:
pixels[x, y] = (0, 0, 0, 0)
return rgba
def remove_small_components(image: Image.Image, min_component_pixels: int) -> Image.Image:
if min_component_pixels <= 0:
return image
rgba = image.convert("RGBA")
alpha = rgba.getchannel("A")
width, height = rgba.size
alpha_pixels = alpha.load()
rgba_pixels = rgba.load()
visited: set[tuple[int, int]] = set()
for y in range(height):
for x in range(width):
if alpha_pixels[x, y] == 0 or (x, y) in visited:
continue
queue: deque[tuple[int, int]] = deque([(x, y)])
visited.add((x, y))
component: list[tuple[int, int]] = []
while queue:
cx, cy = queue.popleft()
component.append((cx, cy))
for nx, ny in ((cx - 1, cy), (cx + 1, cy), (cx, cy - 1), (cx, cy + 1)):
if 0 <= nx < width and 0 <= ny < height:
if alpha_pixels[nx, ny] == 0 or (nx, ny) in visited:
continue
visited.add((nx, ny))
queue.append((nx, ny))
if len(component) < min_component_pixels:
for px, py in component:
r, g, b, _ = rgba_pixels[px, py]
rgba_pixels[px, py] = (r, g, b, 0)
return rgba
def normalize_product_image(
image: Image.Image,
canvas_size: int,
target_width: int,
) -> Image.Image:
rgba = image.convert("RGBA")
bbox = rgba.getchannel("A").getbbox()
if bbox is None:
return Image.new("RGBA", (canvas_size, canvas_size), (0, 0, 0, 0))
subject = rgba.crop(bbox)
if subject.height > subject.width:
subject = subject.rotate(-90, expand=True, resample=Image.Resampling.BICUBIC)
rotated_bbox = subject.getchannel("A").getbbox()
if rotated_bbox is not None:
subject = subject.crop(rotated_bbox)
scale = target_width / subject.width
subject = subject.resize(
(target_width, max(1, int(round(subject.height * scale)))),
Image.Resampling.LANCZOS,
)
canvas = Image.new("RGBA", (canvas_size, canvas_size), (0, 0, 0, 0))
offset_x = (canvas_size - subject.width) // 2
offset_y = (canvas_size - subject.height) // 2
canvas.alpha_composite(subject, (offset_x, offset_y))
return canvas
def finalize_product_image(
image: Image.Image,
canvas_size: int,
target_width: int,
min_component_pixels: int,
) -> Image.Image:
transparent = make_transparent_from_borders(image)
cleaned = remove_small_components(transparent, min_component_pixels)
return normalize_product_image(cleaned, canvas_size=canvas_size, target_width=target_width)
def save_first_image_part(
response,
dst: Path,
canvas_size: int,
target_width: int,
min_component_pixels: int,
) -> None:
parts = getattr(response, "parts", None)
if parts is None and getattr(response, "candidates", None):
parts = response.candidates[0].content.parts
if not parts:
raise RuntimeError("Model returned no content parts.")
for part in parts:
inline_data = getattr(part, "inline_data", None)
if inline_data is None and isinstance(part, dict):
inline_data = part.get("inline_data")
if inline_data is None:
continue
if hasattr(part, "as_image"):
image = to_pil_image(part.as_image())
dst.parent.mkdir(parents=True, exist_ok=True)
finalize_product_image(
image,
canvas_size=canvas_size,
target_width=target_width,
min_component_pixels=min_component_pixels,
).save(dst)
return
data = getattr(inline_data, "data", None)
if data:
dst.parent.mkdir(parents=True, exist_ok=True)
with open(dst, "wb") as handle:
handle.write(data)
with Image.open(dst) as image:
processed = finalize_product_image(
image,
canvas_size=canvas_size,
target_width=target_width,
min_component_pixels=min_component_pixels,
)
processed.save(dst.with_suffix(".png"))
if dst.suffix.lower() != ".png":
dst.unlink(missing_ok=True)
return
raise RuntimeError("Model returned text only and no edited image.")
def process_image(
src: Path,
dst: Path,
client,
model: str,
canvas_size: int,
target_width: int,
min_component_pixels: int,
) -> None:
with Image.open(src).convert("RGBA") as image:
response = client.models.generate_content(
model=model,
contents=[PROMPT, image],
)
save_first_image_part(
response,
dst,
canvas_size=canvas_size,
target_width=target_width,
min_component_pixels=min_component_pixels,
)
def parse_args() -> argparse.Namespace:
parser = argparse.ArgumentParser(
description="Cut out product images with Gemini and normalize them to square transparent PNGs."
)
parser.add_argument("input_dir", type=Path)
parser.add_argument("output_dir", type=Path)
parser.add_argument("--model", default="gemini-2.5-flash-image")
parser.add_argument("--canvas-size", type=int, default=DEFAULT_CANVAS_SIZE)
parser.add_argument("--target-width", type=int, default=DEFAULT_TARGET_WIDTH)
parser.add_argument("--min-component-pixels", type=int, default=DEFAULT_MIN_COMPONENT_PIXELS)
parser.add_argument("--overwrite", action="store_true")
return parser.parse_args()
def main() -> None:
args = parse_args()
api_key = os.environ.get("GEMINI_API_KEY")
if not api_key:
raise SystemExit("Missing GEMINI_API_KEY environment variable.")
if not args.input_dir.is_dir():
raise SystemExit(f"Input directory does not exist: {args.input_dir}")
if args.canvas_size <= 0:
raise SystemExit("--canvas-size must be positive.")
if args.target_width <= 0 or args.target_width > args.canvas_size:
raise SystemExit("--target-width must be positive and no larger than --canvas-size.")
if args.min_component_pixels < 0:
raise SystemExit("--min-component-pixels must be >= 0.")
args.output_dir.mkdir(parents=True, exist_ok=True)
client = genai.Client(api_key=api_key)
for src in sorted(args.input_dir.iterdir()):
if not src.is_file() or src.suffix.lower() not in SUPPORTED_EXTENSIONS:
continue
dst = args.output_dir / f"{src.stem}.png"
if dst.exists() and not args.overwrite:
print(f"skip {dst}")
continue
process_image(
src,
dst,
client,
args.model,
canvas_size=args.canvas_size,
target_width=args.target_width,
min_component_pixels=args.min_component_pixels,
)
print(dst)
if __name__ == "__main__":
main()
|