144 lines
5.5 KiB
Python
144 lines
5.5 KiB
Python
from fastapi import APIRouter, HTTPException, BackgroundTasks
|
||
from pydantic import BaseModel
|
||
from typing import Optional
|
||
from pathlib import Path
|
||
import uuid
|
||
import traceback
|
||
import time
|
||
from app.services.tts_service import TTSService
|
||
from app.services.video_service import VideoService
|
||
from app.services.lipsync_service import LipSyncService
|
||
from app.core.config import settings
|
||
|
||
router = APIRouter()
|
||
|
||
class GenerateRequest(BaseModel):
|
||
text: str
|
||
voice: str = "zh-CN-YunxiNeural"
|
||
material_path: str
|
||
|
||
tasks = {} # In-memory task store
|
||
|
||
# 缓存 LipSync 服务实例和健康状态
|
||
_lipsync_service: Optional[LipSyncService] = None
|
||
_lipsync_ready: Optional[bool] = None
|
||
_lipsync_last_check: float = 0
|
||
|
||
def _get_lipsync_service() -> LipSyncService:
|
||
"""获取或创建 LipSync 服务实例（单例模式，避免重复初始化）"""
|
||
global _lipsync_service
|
||
if _lipsync_service is None:
|
||
_lipsync_service = LipSyncService()
|
||
return _lipsync_service
|
||
|
||
async def _check_lipsync_ready(force: bool = False) -> bool:
|
||
"""检查 LipSync 是否就绪（带缓存，5分钟内不重复检查）"""
|
||
global _lipsync_ready, _lipsync_last_check
|
||
|
||
now = time.time()
|
||
# 5分钟缓存
|
||
if not force and _lipsync_ready is not None and (now - _lipsync_last_check) < 300:
|
||
return _lipsync_ready
|
||
|
||
lipsync = _get_lipsync_service()
|
||
health = await lipsync.check_health()
|
||
_lipsync_ready = health.get("ready", False)
|
||
_lipsync_last_check = now
|
||
print(f"[LipSync] Health check: ready={_lipsync_ready}")
|
||
return _lipsync_ready
|
||
|
||
async def _process_video_generation(task_id: str, req: GenerateRequest):
|
||
try:
|
||
start_time = time.time()
|
||
|
||
# Resolve path if it's relative
|
||
input_material_path = Path(req.material_path)
|
||
if not input_material_path.is_absolute():
|
||
input_material_path = settings.BASE_DIR.parent / req.material_path
|
||
|
||
tasks[task_id]["status"] = "processing"
|
||
tasks[task_id]["progress"] = 5
|
||
tasks[task_id]["message"] = "正在初始化..."
|
||
|
||
# 1. TTS - 进度 5% -> 25%
|
||
tasks[task_id]["message"] = "正在生成语音 (TTS)..."
|
||
tasks[task_id]["progress"] = 10
|
||
|
||
tts = TTSService()
|
||
audio_path = settings.OUTPUT_DIR / f"{task_id}_audio.mp3"
|
||
await tts.generate_audio(req.text, req.voice, str(audio_path))
|
||
|
||
tts_time = time.time() - start_time
|
||
print(f"[Pipeline] TTS completed in {tts_time:.1f}s")
|
||
tasks[task_id]["progress"] = 25
|
||
|
||
# 2. LipSync - 进度 25% -> 85%
|
||
tasks[task_id]["message"] = "正在合成唇形 (LatentSync)..."
|
||
tasks[task_id]["progress"] = 30
|
||
|
||
lipsync = _get_lipsync_service()
|
||
lipsync_video_path = settings.OUTPUT_DIR / f"{task_id}_lipsync.mp4"
|
||
|
||
# 使用缓存的健康检查结果
|
||
lipsync_start = time.time()
|
||
is_ready = await _check_lipsync_ready()
|
||
|
||
if is_ready:
|
||
print(f"[LipSync] Starting LatentSync inference...")
|
||
tasks[task_id]["progress"] = 35
|
||
tasks[task_id]["message"] = "正在运行 LatentSync 推理..."
|
||
await lipsync.generate(str(input_material_path), str(audio_path), str(lipsync_video_path))
|
||
else:
|
||
# Skip lipsync if not available
|
||
print(f"[LipSync] LatentSync not ready, copying original video")
|
||
tasks[task_id]["message"] = "唇形同步不可用，使用原始视频..."
|
||
import shutil
|
||
shutil.copy(str(input_material_path), lipsync_video_path)
|
||
|
||
lipsync_time = time.time() - lipsync_start
|
||
print(f"[Pipeline] LipSync completed in {lipsync_time:.1f}s")
|
||
tasks[task_id]["progress"] = 85
|
||
|
||
# 3. Composition - 进度 85% -> 100%
|
||
tasks[task_id]["message"] = "正在合成最终视频..."
|
||
tasks[task_id]["progress"] = 90
|
||
|
||
video = VideoService()
|
||
final_output = settings.OUTPUT_DIR / f"{task_id}_output.mp4"
|
||
await video.compose(str(lipsync_video_path), str(audio_path), str(final_output))
|
||
|
||
total_time = time.time() - start_time
|
||
print(f"[Pipeline] Total generation time: {total_time:.1f}s")
|
||
|
||
tasks[task_id]["status"] = "completed"
|
||
tasks[task_id]["progress"] = 100
|
||
tasks[task_id]["message"] = f"生成完成！耗时 {total_time:.0f} 秒"
|
||
tasks[task_id]["output"] = str(final_output)
|
||
tasks[task_id]["download_url"] = f"/outputs/{final_output.name}"
|
||
|
||
except Exception as e:
|
||
tasks[task_id]["status"] = "failed"
|
||
tasks[task_id]["message"] = f"错误: {str(e)}"
|
||
tasks[task_id]["error"] = traceback.format_exc()
|
||
|
||
@router.post("/generate")
|
||
async def generate_video(req: GenerateRequest, background_tasks: BackgroundTasks):
|
||
task_id = str(uuid.uuid4())
|
||
tasks[task_id] = {"status": "pending", "task_id": task_id, "progress": 0}
|
||
background_tasks.add_task(_process_video_generation, task_id, req)
|
||
return {"task_id": task_id}
|
||
|
||
@router.get("/tasks/{task_id}")
|
||
async def get_task(task_id: str):
|
||
return tasks.get(task_id, {"status": "not_found"})
|
||
|
||
@router.get("/tasks")
|
||
async def list_tasks():
|
||
return {"tasks": list(tasks.values())}
|
||
|
||
@router.get("/lipsync/health")
|
||
async def lipsync_health():
|
||
"""获取 LipSync 服务健康状态"""
|
||
lipsync = _get_lipsync_service()
|
||
return await lipsync.check_health()
|