"""生成两张 448x448 测试图(纯标准库,不依赖 PIL),供 VLM 带图请求使用。 - orange: 纯橙色。模型若真"看到"图,问颜色应答橙色;瞎猜则说明视觉链路没通。 - square: 白底黑方块。用于形状/内容识别的第二个判别样本。 输出 test_images.json,内容为 OpenAI image_url 用的 data URI。 """ import base64 import json import os import struct import zlib def png_chunk(tag, data): return ( struct.pack(">I", len(data)) + tag + data + struct.pack(">I", zlib.crc32(tag + data) & 0xFFFFFFFF) ) def write_png(w, h, pixel): raw = bytearray() for y in range(h): raw.append(0) # filter type 0 (None) for x in range(w): raw.extend(pixel(x, y)) comp = zlib.compress(bytes(raw), 9) return ( b"\x89PNG\r\n\x1a\n" + png_chunk(b"IHDR", struct.pack(">IIBBBBB", w, h, 8, 2, 0, 0, 0)) + png_chunk(b"IDAT", comp) + png_chunk(b"IEND", b"") ) def main(): # 448x448:与 vision 模型输入尺寸一致,避免 server 额外缩放。 w = h = 448 orange = write_png(w, h, lambda x, y: (255, 128, 0)) def square_px(x, y): if 144 <= x < 304 and 144 <= y < 304: return (0, 0, 0) return (255, 255, 255) square = write_png(w, h, square_px) out = { "orange": "data:image/png;base64," + base64.b64encode(orange).decode(), "square": "data:image/png;base64," + base64.b64encode(square).decode(), } path = os.path.join(os.path.dirname(os.path.abspath(__file__)), "test_images.json") with open(path, "w") as f: json.dump(out, f) print("orange png bytes:", len(orange), "square png bytes:", len(square)) print("orange data uri len:", len(out["orange"])) print("square data uri len:", len(out["square"])) print("saved:", path) if __name__ == "__main__": main()