sophhub 0.4.19 → 0.4.21

package/skills/sophnet-video-generate/src/scripts/gen_video.py

@@ -1,321 +1,321 @@
-#!/usr/bin/env python3
-"""
-Sophnet Video Generation Script
-Supports text-to-video and image-to-video; default model is Seedance unless the user specifies another model.
-"""
-import os
-import sys
-import subprocess
-import argparse
-import json
-import time
-import requests
-from typing import Optional
-import sophnet_tools
-
-# API Configuration
-SOPH_API_KEY = sophnet_tools.get_api_key()
-if SOPH_API_KEY is None:
-    print("错误: 未找到 Sophnet API Key，请确保已正确配置环境变量 SOPH_API_KEY")
-    sys.exit(1)
-GENERATE_URL = "https://www.sophnet.com/api/open-apis/projects/easyllms/videogenerator/generate"
-
-def create_request(
-    prompt: Optional[str],
-    model: str = "Seedance-2.0",
-    negative_prompt: Optional[str] = None,
-    first_frame_url: Optional[str] = None,
-    last_frame_url: Optional[str] = None,
-    size: str = "1280x720",
-    duration: int = 5,
-    generate_audio: bool = True,
-    draft: bool = False
-) -> dict:
-    """Build request body for video generation."""
-    content = []
-
-    # Add text content
-    if prompt:
-        text_content = {"type": "text", "text": prompt}
-        if negative_prompt:
-            text_content["negative_prompt"] = negative_prompt
-        content.append(text_content)
-
-    # Add first frame
-    if first_frame_url:
-        content.append({
-            "type": "image_url",
-            "image_url": {"url": first_frame_url},
-            "role": "first_frame"
-        })
-        # Modality fix only: same family T2V + image → I2V (does not replace unrelated user model choices).
-        if model == "happyhorse-1.0-t2v":
-            model = "happyhorse-1.0-i2v"
-        elif model == "Wan2.6-T2V":
-            model = "Wan2.6-I2V"
-
-        # Add last frame
-        if last_frame_url:
-            content.append({
-                "type": "image_url",
-                "image_url": {"url": last_frame_url},
-                "role": "last_frame"
-            })
-
-    # Build parameters.
-    # Seedance uses resolution levels (e.g. 720p/1080p), while some other models accept size (e.g. 1280*720).
-    def infer_resolution_from_size(raw_size: str) -> str:
-        normalized = raw_size.lower().replace("*", "x")
-        if normalized in {"1920x1080", "1080x1920"}:
-            return "1080p"
-        if normalized in {"1280x720", "720x1280", "1088x832", "832x1088", "960x960"}:
-            return "720p"
-        return "720p"
-
-    parameters = {"duration": duration}
-    if model in {"Seedance-2.0", "Seedance-2.0-Fast", "Seedance-1.5-Pro"}:
-        parameters["resolution"] = infer_resolution_from_size(size)
-    else:
-        parameters["size"] = size.replace("x", "*")
-
-    return {"model": model, "content": content, "parameters": parameters}
-
-
-def make_request(req_data: dict) -> dict:
-    """Make HTTP request with authentication."""
-    headers = {
-        "Authorization": f"Bearer {SOPH_API_KEY}",
-        "Content-Type": "application/json"
-    }
-    try:
-        response = requests.request(
-            "POST",
-            GENERATE_URL,
-            data=json.dumps(req_data).encode("utf-8"),
-            headers=headers,
-            timeout=60
-        )
-        if response.status_code == 200:
-            return response.json()
-        else:
-            print(f"HTTP请求失败，状态码: {response.status_code}, 响应内容: {response.text}")
-            return None
-    except requests.exceptions.RequestException as e:
-        print(f"HTTP请求超时: {e}")
-        return None
-
-
-def make_get_request(task_id: str) -> dict:
-    """Make GET request with authentication."""
-    headers = {
-        "Authorization": f"Bearer {SOPH_API_KEY}",
-        "Content-Type": "application/json"
-    }
-    url = f"{GENERATE_URL}/{task_id}"
-    response = requests.request("GET", url, headers=headers, timeout=60)
-    if response.status_code == 200:
-        return response.json().get("result", {})
-    else:
-        print(f"HTTP请求失败，状态码: {response.status_code}, 响应内容: {response.text}")
-        return None
-
-
-def is_url(path: str) -> bool:
-    """Check if the input string is a URL."""
-    return path.startswith(("http://", "https://"))
-
-
-# 使用浏览器式请求头，避免 CDN/OSS 因 User-Agent 拒绝下载
-DOWNLOAD_HEADERS = {
-    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
-    "Accept": "*/*",
-    "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
-}
-
-
-def get_file_with_requests(url: str, result_name: str, result_path: str) -> bool:
-    """使用 requests 下载文件（带浏览器请求头，避免被服务器拒绝）。"""
-    try:
-        out_dir = os.path.expanduser(result_path)
-        os.makedirs(out_dir, exist_ok=True)
-        out_path = os.path.join(out_dir, result_name)
-        resp = requests.get(url, headers=DOWNLOAD_HEADERS, timeout=30, stream=True)
-        resp.raise_for_status()
-        with open(out_path, "wb") as f:
-            for chunk in resp.iter_content(chunk_size=8192):
-                if chunk:
-                    f.write(chunk)
-        return os.path.isfile(out_path) and os.path.getsize(out_path) > 0
-    except requests.exceptions.RequestException as e:
-        print(f"requests 下载失败: {e}")
-        return False
-    except Exception as e:
-        print(f"下载过程中发生异常: {e}")
-        return False
-
-
-def get_file_with_wget(url: str, result_name: str, result_path: str) -> bool:
-    """Download file using wget (with browser User-Agent)."""
-    try:
-        os.makedirs(os.path.expanduser(result_path), exist_ok=True)
-        out_file = os.path.join(os.path.expanduser(result_path), result_name)
-        user_agent = DOWNLOAD_HEADERS["User-Agent"]
-        result = subprocess.run(
-            ["wget", "-O", out_file,
-             "--tries=1", "--timeout=30",
-             f"--user-agent={user_agent}",
-             url],
-            capture_output=True,
-            text=True
-        )
-        if result.returncode == 0 and os.path.isfile(out_file) and os.path.getsize(out_file) > 0:
-            return True
-        else:
-            print(f"wget 下载失败，返回码: {result.returncode}, 标准输出: {result.stdout}, 标准错误: {result.stderr}")
-            return False
-    except Exception as e:
-        print(f"执行 wget 过程中发生异常: {e}")
-        return False
-
-
-def gen_video(
-    prompt: str,
-    model: str = "Seedance-2.0",
-    size: str = "1280*720",
-    duration: int = 5,
-    first_frame: Optional[str] = None,
-) -> str:
-    """Generate video using Sophnet Video Generation API."""
-    result_video_url = None
-    input_image = None
-    local_video_url = None
-    result_path = "/home/node/.openclaw/workspace/media/inbound/videos/"
-    # Handle first frame
-    if first_frame:
-        if is_url(first_frame):
-            input_image = first_frame
-        elif os.path.isfile(first_frame):
-            input_image = sophnet_tools.upload_oss(first_frame) 
-            if input_image is None:
-                print("上传第一帧图片失败")
-                sys.exit(1)
-    # Build request
-    request_body = create_request(
-        model=model,
-        prompt=prompt,
-        first_frame_url=input_image,
-        size=size,
-        duration=duration,
-    )
-    print(json.dumps(request_body, indent=2))
-
-    request = make_request(request_body)
-    if request is None:
-        return result_video_url, local_video_url  
-    if request.get("status") != 0:
-        print(f"视频生成失败，错误信息: {request.get('message', '未知错误')}")
-        return result_video_url, local_video_url
-    task_id = request.get("result", {}).get("task_id")
-    if not task_id:
-        print("视频生成失败，未返回任务ID")
-        return result_video_url
-    print(f"视频生成请求已提交，任务ID: {task_id}")  
-    # Poll for completion
-    time_start = time.time()
-    while True:
-        request = make_get_request(task_id)
-        if request is None:
-            print("获取任务状态失败")
-            return result_video_url, local_video_url
-        
-        if request.get("status") == "succeeded":
-            video_url = request.get("content", {}).get("video_url")
-            if video_url:
-                if get_file_with_requests(video_url, result_name=f"{task_id}.mp4", result_path=result_path):
-                    local_video_url = os.path.join(os.path.expanduser(result_path), f"{task_id}.mp4")
-                    # Re-upload to get a persistent URL
-                    result_video_url = sophnet_tools.upload_oss(local_video_url)
-                    if result_video_url:
-                        return result_video_url, local_video_url
-                    else:
-                        return video_url, local_video_url
-                else:
-                    return video_url, local_video_url
-            else:
-                print(f"视频生成失败")
-                return None, local_video_url  # Return the direct URL if download fails
-        else:
-            print(f"当前状态: {request}")
-            if request.get("status", "").find("failed") != -1:
-                print(f"视频生成失败，错误信息: {request.get('status', '未知错误')}")
-                return result_video_url, local_video_url          
-            print(f"视频生成中，当前状态: {request.get('status', '未知状态')}")           
-            if time.time() - time_start > 300:  # 5分钟超时
-                print("视频生成超时")
-                return result_video_url, local_video_url       
-            time.sleep(5)
-
-if __name__ == "__main__":
-    # Listed for UX hints only; unknown models are still sent to the API as the user passed them.
-    supported_models = [
-        "happyhorse-1.0-t2v",
-        "happyhorse-1.0-i2v",
-        "Wan2.6-T2V",
-        "Wan2.6-I2V",
-        "ViduQ2-pro",
-        "Seedance-2.0",
-        "Seedance-2.0-Fast",
-        "Seedance-1.5-Pro",
-    ]
-    parser = argparse.ArgumentParser(
-        description="Generate videos using Sophnet Video Generation API"
-    )
-    parser.add_argument("--prompt", help="Text prompt (required for text-to-video)")
-    parser.add_argument("--model", type=str, default="Seedance-2.0",
-                       help="Model name. Defaults to Seedance-2.0")
-    parser.add_argument("--size", type=str, default="1280*720", help="Resolution (default: 1280*720)")
-    parser.add_argument("--duration", type=int, default=5, help="Video duration in seconds (default: 5)")
-    parser.add_argument("--first-frame", type=str, help="First frame image URL or path")
-    parser.add_argument("--generate-audio", action="store_true", help="Generate audio")
-    args = parser.parse_args()
-
-    model = args.model
-    # HappyHorse default: T2V + image → I2V (API expects I2V when a frame is supplied).
-    if args.first_frame and model == "happyhorse-1.0-t2v":
-        model = "happyhorse-1.0-i2v"
-    # Friendly name normalization only (canonical Vidu / Seedance names).
-    elif model.find("ViduQ2") != -1:
-        model = "ViduQ2-pro"
-    elif model.strip().lower() == "seedance":
-        model = "Seedance-2.0"
-    elif model.strip().lower() == "seedance-fast":
-        model = "Seedance-2.0-Fast"
-    elif model not in supported_models:
-        print(f"提示: 模型 '{args.model}' 不在内置常用列表中，将按您指定的名称原样调用 API。")
-    
-    result_url, local_video_url = gen_video(
-        args.prompt,
-        model,
-        args.size,
-        args.duration,
-        args.first_frame,
-    )
-    
-    if result_url:
-        print(f"\n您的视频提示词为: {args.prompt}")
-        print(f"视频生成成功: {result_url}")
-        print(f"视频本地保存路径: {local_video_url}")
-        print(f"提示: 视频保存24小时，请及时下载")
-        
-        # 生成支持的模型列表（排除当前使用的模型）
-        other_models = [m for m in supported_models if m != model]
-        other_models_str = "、".join(other_models)
-        print(f"当前使用的模型为 {model}，还支持 {other_models_str}")
-        print(f"如果想要指定模型，可以直接对我说：使用 [模型名称] 模型，生成 [视频描述]")
-        print(
-            "提示: 常用模型示例: happyhorse-1.0-t2v、happyhorse-1.0-i2v、"
-            "Wan2.6-T2V、Wan2.6-I2V、ViduQ2-pro、Seedance-2.0、Seedance-2.0-Fast、Seedance-1.5-Pro（也可传入文档中的其他模型名）"
-        )
-    else:
-        print("\n视频生成失败")
-        sys.exit(1)
+#!/usr/bin/env python3
+"""
+Sophnet Video Generation Script
+Supports text-to-video and image-to-video; default model is Seedance unless the user specifies another model.
+"""
+import os
+import sys
+import subprocess
+import argparse
+import json
+import time
+import requests
+from typing import Optional
+import sophnet_tools
+
+# API Configuration
+SOPH_API_KEY = sophnet_tools.get_api_key()
+if SOPH_API_KEY is None:
+    print("错误: 未找到 Sophnet API Key，请确保已正确配置环境变量 SOPH_API_KEY")
+    sys.exit(1)
+GENERATE_URL = "https://www.sophnet.com/api/open-apis/projects/easyllms/videogenerator/generate"
+
+def create_request(
+    prompt: Optional[str],
+    model: str = "Seedance-2.0",
+    negative_prompt: Optional[str] = None,
+    first_frame_url: Optional[str] = None,
+    last_frame_url: Optional[str] = None,
+    size: str = "1280x720",
+    duration: int = 5,
+    generate_audio: bool = True,
+    draft: bool = False
+) -> dict:
+    """Build request body for video generation."""
+    content = []
+
+    # Add text content
+    if prompt:
+        text_content = {"type": "text", "text": prompt}
+        if negative_prompt:
+            text_content["negative_prompt"] = negative_prompt
+        content.append(text_content)
+
+    # Add first frame
+    if first_frame_url:
+        content.append({
+            "type": "image_url",
+            "image_url": {"url": first_frame_url},
+            "role": "first_frame"
+        })
+        # Modality fix only: same family T2V + image → I2V (does not replace unrelated user model choices).
+        if model == "happyhorse-1.0-t2v":
+            model = "happyhorse-1.0-i2v"
+        elif model == "Wan2.6-T2V":
+            model = "Wan2.6-I2V"
+
+        # Add last frame
+        if last_frame_url:
+            content.append({
+                "type": "image_url",
+                "image_url": {"url": last_frame_url},
+                "role": "last_frame"
+            })
+
+    # Build parameters.
+    # Seedance uses resolution levels (e.g. 720p/1080p), while some other models accept size (e.g. 1280*720).
+    def infer_resolution_from_size(raw_size: str) -> str:
+        normalized = raw_size.lower().replace("*", "x")
+        if normalized in {"1920x1080", "1080x1920"}:
+            return "1080p"
+        if normalized in {"1280x720", "720x1280", "1088x832", "832x1088", "960x960"}:
+            return "720p"
+        return "720p"
+
+    parameters = {"duration": duration}
+    if model in {"Seedance-2.0", "Seedance-2.0-Fast", "Seedance-1.5-Pro"}:
+        parameters["resolution"] = infer_resolution_from_size(size)
+    else:
+        parameters["size"] = size.replace("x", "*")
+
+    return {"model": model, "content": content, "parameters": parameters}
+
+
+def make_request(req_data: dict) -> dict:
+    """Make HTTP request with authentication."""
+    headers = {
+        "Authorization": f"Bearer {SOPH_API_KEY}",
+        "Content-Type": "application/json"
+    }
+    try:
+        response = requests.request(
+            "POST",
+            GENERATE_URL,
+            data=json.dumps(req_data).encode("utf-8"),
+            headers=headers,
+            timeout=60
+        )
+        if response.status_code == 200:
+            return response.json()
+        else:
+            print(f"HTTP请求失败，状态码: {response.status_code}, 响应内容: {response.text}")
+            return None
+    except requests.exceptions.RequestException as e:
+        print(f"HTTP请求超时: {e}")
+        return None
+
+
+def make_get_request(task_id: str) -> dict:
+    """Make GET request with authentication."""
+    headers = {
+        "Authorization": f"Bearer {SOPH_API_KEY}",
+        "Content-Type": "application/json"
+    }
+    url = f"{GENERATE_URL}/{task_id}"
+    response = requests.request("GET", url, headers=headers, timeout=60)
+    if response.status_code == 200:
+        return response.json().get("result", {})
+    else:
+        print(f"HTTP请求失败，状态码: {response.status_code}, 响应内容: {response.text}")
+        return None
+
+
+def is_url(path: str) -> bool:
+    """Check if the input string is a URL."""
+    return path.startswith(("http://", "https://"))
+
+
+# 使用浏览器式请求头，避免 CDN/OSS 因 User-Agent 拒绝下载
+DOWNLOAD_HEADERS = {
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36",
+    "Accept": "*/*",
+    "Accept-Language": "zh-CN,zh;q=0.9,en;q=0.8",
+}
+
+
+def get_file_with_requests(url: str, result_name: str, result_path: str) -> bool:
+    """使用 requests 下载文件（带浏览器请求头，避免被服务器拒绝）。"""
+    try:
+        out_dir = os.path.expanduser(result_path)
+        os.makedirs(out_dir, exist_ok=True)
+        out_path = os.path.join(out_dir, result_name)
+        resp = requests.get(url, headers=DOWNLOAD_HEADERS, timeout=30, stream=True)
+        resp.raise_for_status()
+        with open(out_path, "wb") as f:
+            for chunk in resp.iter_content(chunk_size=8192):
+                if chunk:
+                    f.write(chunk)
+        return os.path.isfile(out_path) and os.path.getsize(out_path) > 0
+    except requests.exceptions.RequestException as e:
+        print(f"requests 下载失败: {e}")
+        return False
+    except Exception as e:
+        print(f"下载过程中发生异常: {e}")
+        return False
+
+
+def get_file_with_wget(url: str, result_name: str, result_path: str) -> bool:
+    """Download file using wget (with browser User-Agent)."""
+    try:
+        os.makedirs(os.path.expanduser(result_path), exist_ok=True)
+        out_file = os.path.join(os.path.expanduser(result_path), result_name)
+        user_agent = DOWNLOAD_HEADERS["User-Agent"]
+        result = subprocess.run(
+            ["wget", "-O", out_file,
+             "--tries=1", "--timeout=30",
+             f"--user-agent={user_agent}",
+             url],
+            capture_output=True,
+            text=True
+        )
+        if result.returncode == 0 and os.path.isfile(out_file) and os.path.getsize(out_file) > 0:
+            return True
+        else:
+            print(f"wget 下载失败，返回码: {result.returncode}, 标准输出: {result.stdout}, 标准错误: {result.stderr}")
+            return False
+    except Exception as e:
+        print(f"执行 wget 过程中发生异常: {e}")
+        return False
+
+
+def gen_video(
+    prompt: str,
+    model: str = "Seedance-2.0",
+    size: str = "1280*720",
+    duration: int = 5,
+    first_frame: Optional[str] = None,
+) -> str:
+    """Generate video using Sophnet Video Generation API."""
+    result_video_url = None
+    input_image = None
+    local_video_url = None
+    result_path = "/home/node/.openclaw/workspace/media/inbound/videos/"
+    # Handle first frame
+    if first_frame:
+        if is_url(first_frame):
+            input_image = first_frame
+        elif os.path.isfile(first_frame):
+            input_image = sophnet_tools.upload_oss(first_frame) 
+            if input_image is None:
+                print("上传第一帧图片失败")
+                sys.exit(1)
+    # Build request
+    request_body = create_request(
+        model=model,
+        prompt=prompt,
+        first_frame_url=input_image,
+        size=size,
+        duration=duration,
+    )
+    print(json.dumps(request_body, indent=2))
+
+    request = make_request(request_body)
+    if request is None:
+        return result_video_url, local_video_url  
+    if request.get("status") != 0:
+        print(f"视频生成失败，错误信息: {request.get('message', '未知错误')}")
+        return result_video_url, local_video_url
+    task_id = request.get("result", {}).get("task_id")
+    if not task_id:
+        print("视频生成失败，未返回任务ID")
+        return result_video_url
+    print(f"视频生成请求已提交，任务ID: {task_id}")  
+    # Poll for completion
+    time_start = time.time()
+    while True:
+        request = make_get_request(task_id)
+        if request is None:
+            print("获取任务状态失败")
+            return result_video_url, local_video_url
+        
+        if request.get("status") == "succeeded":
+            video_url = request.get("content", {}).get("video_url")
+            if video_url:
+                if get_file_with_requests(video_url, result_name=f"{task_id}.mp4", result_path=result_path):
+                    local_video_url = os.path.join(os.path.expanduser(result_path), f"{task_id}.mp4")
+                    # Re-upload to get a persistent URL
+                    result_video_url = sophnet_tools.upload_oss(local_video_url)
+                    if result_video_url:
+                        return result_video_url, local_video_url
+                    else:
+                        return video_url, local_video_url
+                else:
+                    return video_url, local_video_url
+            else:
+                print(f"视频生成失败")
+                return None, local_video_url  # Return the direct URL if download fails
+        else:
+            print(f"当前状态: {request}")
+            if request.get("status", "").find("failed") != -1:
+                print(f"视频生成失败，错误信息: {request.get('status', '未知错误')}")
+                return result_video_url, local_video_url          
+            print(f"视频生成中，当前状态: {request.get('status', '未知状态')}")           
+            if time.time() - time_start > 300:  # 5分钟超时
+                print("视频生成超时")
+                return result_video_url, local_video_url       
+            time.sleep(5)
+
+if __name__ == "__main__":
+    # Listed for UX hints only; unknown models are still sent to the API as the user passed them.
+    supported_models = [
+        "happyhorse-1.0-t2v",
+        "happyhorse-1.0-i2v",
+        "Wan2.6-T2V",
+        "Wan2.6-I2V",
+        "ViduQ2-pro",
+        "Seedance-2.0",
+        "Seedance-2.0-Fast",
+        "Seedance-1.5-Pro",
+    ]
+    parser = argparse.ArgumentParser(
+        description="Generate videos using Sophnet Video Generation API"
+    )
+    parser.add_argument("--prompt", help="Text prompt (required for text-to-video)")
+    parser.add_argument("--model", type=str, default="Seedance-2.0",
+                       help="Model name. Defaults to Seedance-2.0")
+    parser.add_argument("--size", type=str, default="1280*720", help="Resolution (default: 1280*720)")
+    parser.add_argument("--duration", type=int, default=5, help="Video duration in seconds (default: 5)")
+    parser.add_argument("--first-frame", type=str, help="First frame image URL or path")
+    parser.add_argument("--generate-audio", action="store_true", help="Generate audio")
+    args = parser.parse_args()
+
+    model = args.model
+    # HappyHorse default: T2V + image → I2V (API expects I2V when a frame is supplied).
+    if args.first_frame and model == "happyhorse-1.0-t2v":
+        model = "happyhorse-1.0-i2v"
+    # Friendly name normalization only (canonical Vidu / Seedance names).
+    elif model.find("ViduQ2") != -1:
+        model = "ViduQ2-pro"
+    elif model.strip().lower() == "seedance":
+        model = "Seedance-2.0"
+    elif model.strip().lower() == "seedance-fast":
+        model = "Seedance-2.0-Fast"
+    elif model not in supported_models:
+        print(f"提示: 模型 '{args.model}' 不在内置常用列表中，将按您指定的名称原样调用 API。")
+    
+    result_url, local_video_url = gen_video(
+        args.prompt,
+        model,
+        args.size,
+        args.duration,
+        args.first_frame,
+    )
+    
+    if result_url:
+        print(f"\n您的视频提示词为: {args.prompt}")
+        print(f"视频生成成功: {result_url}")
+        print(f"视频本地保存路径: {local_video_url}")
+        print(f"提示: 视频保存24小时，请及时下载")
+        
+        # 生成支持的模型列表（排除当前使用的模型）
+        other_models = [m for m in supported_models if m != model]
+        other_models_str = "、".join(other_models)
+        print(f"当前使用的模型为 {model}，还支持 {other_models_str}")
+        print(f"如果想要指定模型，可以直接对我说：使用 [模型名称] 模型，生成 [视频描述]")
+        print(
+            "提示: 常用模型示例: happyhorse-1.0-t2v、happyhorse-1.0-i2v、"
+            "Wan2.6-T2V、Wan2.6-I2V、ViduQ2-pro、Seedance-2.0、Seedance-2.0-Fast、Seedance-1.5-Pro（也可传入文档中的其他模型名）"
+        )
+    else:
+        print("\n视频生成失败")
+        sys.exit(1)