6d20662cc0
- tools/qwen-vision.py: 阿里百炼通义千问VL视觉模型·智能风格/构图/色调分析·双图对比 - tools/vision-analyzer.py: 本地像素级定量分析·色调直方图·纹理/亮度对比 - LOCAL-SECRETS-PATH: 新增ALIYUN_QWEN_VL_KEY/ENDPOINT变量 - CURRENT.hdlp: 最优路径新增第0步「出图后跑铸渊之眼」 - TCS-GLOBAL-NAV: 新增「看图/视觉分析」关键词→HLDP路径映射 下次醒来→读地图→看到视觉分析锚点→知道有眼睛了
137 lines
4.7 KiB
Python
137 lines
4.7 KiB
Python
#!/usr/bin/env python3
|
||
"""铸渊之眼 · 通义千问视觉分析器
|
||
用阿里百炼 qwen-vl 模型看图片，输出风格/色调/构图分析
|
||
|
||
用法:
|
||
python3 qwen-vision.py <image.jpg> # 单图分析
|
||
python3 qwen-vision.py <image1.jpg> <image2.jpg> # 双图对比
|
||
"""
|
||
|
||
import sys, os, json, base64
|
||
from urllib.request import Request, urlopen
|
||
from urllib.error import URLError
|
||
|
||
# === 配置 ===
|
||
# 从 .env 读 key
|
||
env_path = os.path.expanduser("~/guanghulab/video-ai-system/.env")
|
||
api_key = None
|
||
if os.path.exists(env_path):
|
||
for line in open(env_path):
|
||
line = line.strip()
|
||
if line.startswith("ALIYUN_API_KEY="):
|
||
api_key = line.split("=", 1)[1].strip()
|
||
break
|
||
|
||
if not api_key:
|
||
print(json.dumps({"error": "未找到ALIYUN_API_KEY"}))
|
||
sys.exit(1)
|
||
|
||
# 端点：先试公网，再试北京
|
||
ENDPOINTS = [
|
||
"https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation",
|
||
]
|
||
MODELS = ["qwen-vl-max", "qwen3-vl-plus", "qwen-vl-plus"]
|
||
|
||
def encode_image(path):
|
||
"""读取图片并转为base64 data URI"""
|
||
with open(path, "rb") as f:
|
||
b64 = base64.b64encode(f.read()).decode()
|
||
ext = path.rsplit(".", 1)[-1].lower()
|
||
mime = {"jpg": "jpeg", "jpeg": "jpeg", "png": "png", "webp": "webp"}.get(ext, "jpeg")
|
||
return f"data:image/{mime};base64,{b64}"
|
||
|
||
def call_vision(images, prompt, model, endpoint):
|
||
"""调用视觉模型"""
|
||
content = []
|
||
for img in images:
|
||
content.append({"image": img})
|
||
content.append({"text": prompt})
|
||
|
||
body = {
|
||
"model": model,
|
||
"input": {"messages": [{"role": "user", "content": content}]}
|
||
}
|
||
|
||
req = Request(
|
||
endpoint,
|
||
data=json.dumps(body).encode(),
|
||
headers={
|
||
"Authorization": f"Bearer {api_key}",
|
||
"Content-Type": "application/json"
|
||
}
|
||
)
|
||
|
||
resp = urlopen(req, timeout=60)
|
||
return json.loads(resp.read())
|
||
|
||
def extract_content(response):
|
||
"""从响应中提取文本内容"""
|
||
try:
|
||
return response["output"]["choices"][0]["message"]["content"][0]["text"]
|
||
except:
|
||
return json.dumps(response, ensure_ascii=False)
|
||
|
||
if __name__ == "__main__":
|
||
if len(sys.argv) < 2:
|
||
print("用法: qwen-vision.py <image> [image2]")
|
||
sys.exit(1)
|
||
|
||
images = [encode_image(p) for p in sys.argv[1:]]
|
||
|
||
if len(images) == 1:
|
||
prompt = """请详细分析这张图片的视觉特征，输出JSON格式：
|
||
{
|
||
"style": "渲染风格（如3D动漫/2D手绘/真人写实/UE5游戏等）",
|
||
"color_palette": ["主色调1", "主色调2", "主色调3"],
|
||
"lighting": "光影风格描述",
|
||
"composition": "构图方式（特写/中景/全景/俯视/平视等）",
|
||
"key_elements": ["画面中的关键元素"],
|
||
"text_content": "画面中出现的所有文字内容",
|
||
"mood": "氛围感受"
|
||
}
|
||
只输出JSON，不要其他文字。"""
|
||
else:
|
||
prompt = """请对比这两张图片，输出JSON格式：
|
||
{
|
||
"style_match": true或false,
|
||
"style_match_detail": "两张图渲染风格是否一致的具体说明",
|
||
"color_consistency": "色调是否一致，给出0-100分",
|
||
"composition_match": "构图方式是否协调",
|
||
"key_differences": ["主要差异点"],
|
||
"recommendation": "如果要让第二张图匹配第一张图的风格，建议修改什么"
|
||
}
|
||
只输出JSON，不要其他文字。"""
|
||
|
||
# 尝试不同模型和端点
|
||
result = None
|
||
for model in MODELS:
|
||
for ep in ENDPOINTS:
|
||
try:
|
||
print(f"[尝试] {model} @ {ep[:50]}...", file=sys.stderr)
|
||
resp = call_vision(images, prompt, model, ep)
|
||
content = extract_content(resp)
|
||
# 尝试解析JSON
|
||
try:
|
||
# 提取JSON（可能被markdown包裹）
|
||
if "```json" in content:
|
||
content = content.split("```json")[1].split("```")[0]
|
||
elif "```" in content:
|
||
content = content.split("```")[1].split("```")[0]
|
||
parsed = json.loads(content.strip())
|
||
parsed["_model"] = model
|
||
parsed["_endpoint"] = ep
|
||
print(json.dumps(parsed, ensure_ascii=False, indent=2))
|
||
sys.exit(0)
|
||
except json.JSONDecodeError:
|
||
print(content)
|
||
sys.exit(0)
|
||
except URLError as e:
|
||
print(f"[失败] {model}: {e}", file=sys.stderr)
|
||
continue
|
||
except Exception as e:
|
||
print(f"[异常] {model}: {e}", file=sys.stderr)
|
||
continue
|
||
|
||
print(json.dumps({"error": "所有模型/端点都失败了"}, ensure_ascii=False))
|
||
sys.exit(1)
|