PRINTFILM: AI short-video marketing and AI short-drama creation platform
feat(short-video): 完善参考图生图与分阶段视频制作
yif60ae2253101
diff --git a/README.md b/README.mdindex 064d305..3d942b6 100644--- a/README.md+++ b/README.md@@ -7,7 +7,7 @@> **把故事做成能播的片子** — AI 漫剧与 AI 短视频,从文案到成片。-分步短视频创作:创作设置 → 文案与分镜 → 画面与配音 → 成片预览。默认 3D 动画画风、9:16 竖屏、约 60 秒,各阶段检查与编辑后再继续制作。+分步短视频创作:创作设置 → 文案与分镜 → 参考图生图 → 图生视频 → 合成预览。新建默认 AI 视频、3D 动画画风、9:16 竖屏、约 60 秒,也可选择静图成片,各阶段检查与编辑后再继续制作。**源码**:[github.com/yi1108/printfilm](https://github.com/yi1108/printfilm) · **版本** 0.2.0@@ -50,8 +50,9 @@- 精选四款非真人风格:3D 动画、二维动漫、绘本插画、国风水墨- 输入想法生成文案,或粘贴已有文案;文案可编辑并保存草稿-- 确认文案后生成分镜卡片,逐镜编辑旁白与画面,再生成图片和外部 TTS 配音-- 图片和配音准备好后手动合成;FFmpeg 添加图片运镜和字幕,支持预览、下载+- 确认文案后生成分镜,逐镜编辑旁白与画面;每镜使用固定画风参考图,并参考前镜图片延续角色与视觉风格+- AI 视频模式把每镜图片生成为带声音的镜头视频,支持单镜预览和重生;选择模型与清晰度后分阶段生成,再手动合成成片+- 静图模式生成图片和外部 TTS 配音,FFmpeg 添加图片运镜和字幕;两种模式都支持预览、下载- 制作中可停止,失败时继续补齐缺失素材;离开页面后可回到项目恢复进度- 旧对话项目在任务停止并结算后移交分步编辑,各历史版本保留原素材@@ -68,8 +69,9 @@```选择画风、输入想法或已有文案→ 编辑与保存文案 → 确认后生成分镜- → 检查分镜卡片 → 生成图片与外部 TTS 配音- → 检查画面、试听配音 → 合成运镜、字幕与旁白+ → 检查分镜卡片 → 使用画风参考图生成图片+ → AI 视频:图片生成镜头视频与声音 → 检查并合成+ 静图成片:生成外部 TTS 配音 → 合成运镜、字幕与旁白→ 预览与下载成片```diff --git a/README_EN.md b/README_EN.mdindex af1b8ea..c7ee35b 100644--- a/README_EN.md+++ b/README_EN.md@@ -7,7 +7,7 @@> **Turn stories into videos you can ship** — AI short drama and AI short video, from script to final cut.-Step-by-step short-video creation: settings → copy and storyboard → images and narration → final preview. Defaults: 3D animation, 9:16 portrait and approximately 60 seconds. Review and edit each stage before continuing.+Step-by-step short-video creation: settings → copy and storyboard → reference-guided images → image-to-video → final preview. New projects default to AI video, 3D animation, 9:16 portrait and approximately 60 seconds; still-image production is also available. Review and edit each stage before continuing.**Source:** [github.com/yi1108/printfilm](https://github.com/yi1108/printfilm) · **Version** 0.2.0@@ -50,8 +50,9 @@ Manage short videos as project cards at `/history`, then start a new project at- Four curated styles: 3D animation, 2D anime, picture-book illustration, and ink painting- Generate copy from an idea or paste an existing script; edit and save it as a draft-- Confirm the copy to generate editable storyboard cards, then generate images and external TTS narration-- Review images and audition narration before composing camera motion, captions and audio; preview and download the result+- Confirm the copy to generate editable storyboards; use a fixed style image and previous-shot references to guide each image+- AI video mode generates clips and sound from each shot image, with selectable models, resolution, individual previews and retries before final composition+- Still-image mode retains external TTS, camera motion and captions; both modes support preview and download- Stop production or resume missing media after a failure; saved projects and tasks recover after leaving the page- Existing conversations transfer to the step editor after their producers stop and settle; historical versions retain their media@@ -68,8 +69,9 @@ Users, orders, templates, task center, and model routing.```Choose a style and enter an idea or existing copy→ Edit and save copy → Confirm to generate storyboard cards- → Review storyboard → Generate images and external TTS- → Review images and audition narration → Compose motion and captions+ → Review storyboard → Generate images using style references+ → AI video: Generate clips and sound from images → Review and compose+ Still images: Generate external TTS → Compose motion and captions→ Preview and download the final video```diff --git a/backend/app/api/projects.py b/backend/app/api/projects.pyindex e70221d..6ac9cc2 100644--- a/backend/app/api/projects.py+++ b/backend/app/api/projects.py@@ -53,10 +53,10 @@ from app.services.kepu_projects import list_project_page, project_runtime_viewrouter = APIRouter(tags=["projects"])-def _demote_after_edit(project: Project) -> None:+def _demote_after_edit(project: Project, *, recheck_stage: bool = False) -> None:"""改镜头/配乐后作废成片,并按素材把终态打回 script/assets/videos/compose。"""project.final_video_url = None- if project.status not in {+ if not recheck_stage and project.status not in {ProjectStatus.DONE,ProjectStatus.AUDITING,ProjectStatus.COMPOSING,@@ -470,7 +470,7 @@ async def get_project("/projects/{project_id}",response_model=ProjectOut,summary="修改科普短片项目",- description="需要登录,按请求中提供的字段更新本人的项目。生成期间及对话创作管理的项目不允许在此修改;更改配乐或字幕预设会使现有成片失效。",+ description="需要登录,按请求中提供的字段更新本人的项目。生成期间及对话创作管理的项目不允许在此修改;更改制作模式、配乐或字幕预设会使现有成片失效。制作模式变更后沿用已有素材,按新模式回到待生成或待合成阶段。",response_description="更新后的项目详情",)async def update_project(@@ -526,10 +526,12 @@ async def update_project(data["bgm_lock"] = str(data["bgm_lock"] or "").strip()if "subtitle_preset" in data:data["subtitle_preset"] = str(data["subtitle_preset"] or "").strip()- if "bgm_lock" in data or "subtitle_preset" in data:- _demote_after_edit(project)+ # 按新模式判定下一阶段;保留图片/视频/配音,只作废原模式的成片。+ mode_changed = "pipeline_mode" in data and data["pipeline_mode"] != (project.pipeline_mode or "full")for k, v in data.items():setattr(project, k, v)+ if mode_changed or "bgm_lock" in data or "subtitle_preset" in data:+ _demote_after_edit(project, recheck_stage=mode_changed)await db.commit()return await _get_owned_project(db, project_id, user)diff --git a/backend/app/services/ark.py b/backend/app/services/ark.pyindex 3b5eecf..2101d32 100644--- a/backend/app/services/ark.py+++ b/backend/app/services/ark.py@@ -2149,11 +2149,13 @@ class ArkGateway:# Seedance 2.0: 需要公网 https;本地 /static 先同步上 OSSlocal = storage.local_path_from_url(raw)if local and local.exists():- public = storage.republish_url(raw, sync=True)+ from app.services.kepu_image_references import public_image_reference++ public = await asyncio.to_thread(public_image_reference, raw)if public and str(public).startswith("https://"):return str(public)raise RuntimeError(- "Seedance 需要公网可访问的图片 URL(请启用 OSS 并确保参考图已上传),"+ "Seedance 需要公网可访问的图片 URL(请配置 HTTPS 公网访问地址或启用 OSS 并上传参考图),""本地 /static 图无法被方舟拉取")if raw.startswith("data:"):diff --git a/backend/app/services/kepu_continuity.py b/backend/app/services/kepu_continuity.pyindex 88eb0c1..71b8d5c 100644--- a/backend/app/services/kepu_continuity.py+++ b/backend/app/services/kepu_continuity.py@@ -41,11 +41,9 @@ def _usable_seedream_url(raw: str | None, *, allow_republish: bool = False) -> sif is_tokenfree_image_url(url):return Noneif allow_republish and not (url.startswith("http://") or url.startswith("https://")):- from app.services import storage+ from app.services.kepu_image_references import public_image_reference- url = str(storage.republish_url(url, sync=True) or "").strip()- if is_tokenfree_image_url(url):- return None+ return public_image_reference(url)ok = seedream_ref_urls(url)return ok[0] if ok else None@@ -75,6 +73,14 @@ def _any_shot_image(shot: Any) -> str | None:return None+def video_image_ref(shot: Any) -> str:+ """本镜图生视频首图优先公网/本地落盘图,跳过需要上游鉴权的产物 URL。"""+ for raw in (getattr(shot, "image_url", None), getattr(shot, "image_ark_url", None)):+ if url := _usable_seedream_url(raw):+ return url+ return _any_shot_image(shot) or ""++def shot_last_frame_ref(shot: Any | None) -> str | None:"""上一镜尾帧;TokenFree 任务 URL 跳过,避免下游无鉴权拉不到。"""if shot is None:diff --git a/backend/app/services/kepu_image_references.py b/backend/app/services/kepu_image_references.pynew file mode 100644index 0000000..f0eca3b--- /dev/null+++ b/backend/app/services/kepu_image_references.py@@ -0,0 +1,89 @@+"""短视频画风与主体参考:每镜固定画风图,云端只接收可访问图片。"""+from __future__ import annotations++from typing import Any+from ipaddress import ip_address+from urllib.parse import urlsplit++from app.config import get_settings+from app.services import storage+from app.services.style_lock import seedream_ref_urls+from app.services.tokenfree_image import is_tokenfree_image_url+++def _public_reference(url: str) -> str | None:+ """过滤私网、回环与需要 TokenFree 鉴权的图片地址。"""+ if is_tokenfree_image_url(url) or not seedream_ref_urls(url, limit=1):+ return None+ host = urlsplit(url).hostname or ""+ try:+ if not ip_address(host).is_global:+ return None+ except ValueError:+ if host.endswith(".localhost"):+ return None+ return url+++def public_image_reference(raw: str | None) -> str | None:+ """本地图片同步发布或使用站点公网地址,拒绝鉴权产物与越界路径。"""+ url = str(raw or "").strip()+ if not url or is_tokenfree_image_url(url):+ return None+ if public := _public_reference(url):+ return public+ if not storage.is_local_static_url(url):+ return None+ local = storage.local_path_from_url(url)+ if not local or not local.resolve().is_relative_to(storage.STATIC_ROOT.resolve()) or not local.is_file():+ return None+ published = str(storage.republish_url(url, sync=True) or "")+ return _public_reference(published) or _public_reference(storage.to_public_url(url))+++def project_image_reference_inputs(project: Any) -> tuple[list[str], list[str]]:+ """只读取主体与画风引用槽位;预占计费时不上传文件。"""+ template = getattr(project, "template", None)+ config = getattr(template, "seedream_config", None) or {}+ config = config if isinstance(config, dict) else {}+ styles = config.get("style_ref_urls") or []+ styles = [url.strip() for url in styles if isinstance(url, str) and url.strip()] if isinstance(styles, list) else []+ legacy_refs = config.get("ref_images") or []+ legacy_refs = [url.strip() for url in legacy_refs if isinstance(url, str) and url.strip()] if isinstance(legacy_refs, list) else []+ cover = str(getattr(template, "preview_cover", None) or "").strip()+ if not cover:+ from app.services.creation_templates import CREATION_TEMPLATE_IDS++ template_id = getattr(template, "id", None)+ if template_id in CREATION_TEMPLATE_IDS:+ cover = f"/static/templates/covers/{template_id}.png"+ if not styles and cover:+ styles = [cover]+ subject = str(getattr(project, "ref_image_url", None) or "").strip()+ subjects = list(dict.fromkeys(([subject] if subject else []) + legacy_refs))[:2]+ return subjects, styles+++def project_image_references(project: Any) -> tuple[list[str], list[str]]:+ """解析用户主体图与独立画风图;真实生成不可静默退回纯文字模式。"""+ subjects, styles = project_image_reference_inputs(project)+ settings = get_settings()+ mocked = bool(settings.ark_mock or settings.local_media_mock)++ def resolve(url: str) -> str | None:+ """离线模拟不上传;真实任务仅传公网图。"""+ if mocked and url.startswith("/static/") and ".." not in url.split("/"):+ return url+ return public_image_reference(url)++ subject_refs = [value for url in subjects if (value := resolve(url))]+ style_refs = []+ for url in styles:+ if value := resolve(url):+ style_refs.append(value)+ break+ if subjects and not subject_refs:+ raise ValueError("主体参考图无法访问,请重新上传参考图,或检查公网访问地址和 OSS 配置")+ if styles and not style_refs:+ raise ValueError("画风参考图无法访问,请检查公网访问地址或 OSS 配置后重试")+ return subject_refs, style_refsdiff --git a/backend/app/services/media_models/planning.py b/backend/app/services/media_models/planning.pyindex e2103c1..981828c 100644--- a/backend/app/services/media_models/planning.py+++ b/backend/app/services/media_models/planning.py@@ -22,6 +22,50 @@ def reference_params(payload: dict) -> dict:return {key: payload[key] for key in REFERENCE_FIELDS if key in payload}+def _kepu_stored_reference(*candidates: str | None) -> str | None:+ """Inspect saved refs without publishing files or forwarding private artifacts."""+ from app.services.tokenfree_image import is_tokenfree_image_url+ from app.services.tokenfree_video import is_tokenfree_content_url++ for raw in candidates:+ url = str(raw or "").strip()+ if url and not is_tokenfree_image_url(url) and not is_tokenfree_content_url(url):+ return url+ return None+++def _kepu_stored_image_ref(shot) -> str | None:+ return _kepu_stored_reference(getattr(shot, "image_url", None), getattr(shot, "image_ark_url", None))+++def _kepu_video_refs(shot, previous, pending_video_ids: set[int]) -> list[str]:+ """Reserve future tail slots; the worker supplies their actual URLs later."""+ refs = [_kepu_stored_image_ref(shot) or f"pending://shot-{shot.shot_no}-image"]+ if previous is None:+ return refs+ tail = _kepu_stored_reference(getattr(previous, "last_frame_url", None))+ if previous.id in pending_video_ids or (getattr(previous, "video_url", None) and not tail):+ tail = f"pending://shot-{previous.shot_no}-last-frame"+ extra = tail or _kepu_stored_image_ref(previous)+ if extra:+ refs.append(extra)+ return refs+++def _kepu_image_refs(project, shot, predecessors, pending_image_ids: set[int]) -> dict:+ """Reserve the fixed style board, user image and previous shot without uploading."""+ from app.services.kepu_image_references import project_image_reference_inputs++ subjects, styles = project_image_reference_inputs(project)+ previous = next((item for item in reversed(predecessors)+ if item.id in pending_image_ids or _kepu_stored_image_ref(item)), None)+ if previous is not None:+ ref = (f"pending://shot-{previous.shot_no}-image" if previous.id in pending_image_ids+ else _kepu_stored_image_ref(previous))+ subjects = [ref, *subjects]+ return {"reference_images": list(dict.fromkeys(subjects))[:2], "style_ref_urls": styles[:1]}++async def canvas_video_reference_content(db, task, payload: dict) -> list[dict]:"""Build the same reference slots as the worker without publishing or generating media."""from app.models_drama import DramaProject@@ -80,22 +124,44 @@ async def plan_items(db, task) -> list[dict]:if not project:return []from app.services.kepu_stages import normalize_kepu_pipeline_phase, shot_image_ready, shot_video_ready- from app.services.pipeline import _image_size_for, _project_output_ratio+ from app.services.pipeline import _image_size_for, _kepu_seedance_generate_audio, _project_output_ratio+ from app.services import seedance_segments as segplanphase = normalize_kepu_pipeline_phase(str(p.get("phase") or "script"), project)- shots = project.shots+ all_shots = sorted(project.shots, key=lambda shot: shot.shot_no)+ shots = all_shotsif kind != "project_pipeline":shots = [x for x in shots if x.id == task.shot_id]phase = "assets" if kind == "shot_regen_image" else "videos"+ pending_video_ids = {+ shot.id for shot in shots+ if phase == "videos" and (kind != "project_pipeline" or not shot_video_ready(shot))+ }+ pending_image_ids = {+ shot.id for shot in shots+ if phase == "assets" and (kind != "project_pipeline" or not shot_image_ready(shot))+ }for shot in shots:if phase == "assets" and (kind != "project_pipeline" or not shot_image_ready(shot)):+ predecessors = [previous for previous in all_shots if previous.shot_no < shot.shot_no]add("image", {"size": _image_size_for(project) or settings.ark_image_size,- "aspect_ratio": _project_output_ratio(project) or "1:1"},+ "aspect_ratio": _project_output_ratio(project) or "1:1",+ **_kepu_image_refs(project, shot, predecessors, pending_image_ids)},model=project.image_model, target=shot.id, shot_no=shot.shot_no)if phase == "videos" and (kind != "project_pipeline" or not shot_video_ready(shot)):from app.services.seedance_resolutions import project_video_resolutionresolution = project_video_resolution(project, settings)- add("video", {"duration": int(shot.duration or 5), "resolution": resolution,- "aspect_ratio": _project_output_ratio(project) or "9:16"},+ script = (getattr(shot, "segment_script", "") or getattr(shot, "video_prompt", "") or "").strip()+ duration = segplan.resolve_api_duration(script, fallback=shot.duration or 5,+ lo=settings.seedance_duration_min, hi=settings.seedance_duration_max)+ predecessors = [previous for previous in all_shots if previous.shot_no < shot.shot_no]+ if kind == "shot_regen_video":+ predecessors = [previous for previous in predecessors if _kepu_stored_image_ref(previous)+ or _kepu_stored_reference(getattr(previous, "last_frame_url", None))]+ previous = predecessors[-1] if predecessors else None+ add("video", {"duration": duration, "resolution": resolution,+ "aspect_ratio": _project_output_ratio(project) or settings.ark_video_ratio,+ "generate_audio": _kepu_seedance_generate_audio(project),+ "reference_images": _kepu_video_refs(shot, previous, pending_video_ids)},model=project.video_model, target=shot.id, shot_no=shot.shot_no)return itemsif kind in {"asset_image", "tool_image"}:diff --git a/backend/app/services/pipeline.py b/backend/app/services/pipeline.pyindex b42a9ad..ae096ac 100644--- a/backend/app/services/pipeline.py+++ b/backend/app/services/pipeline.py@@ -30,7 +30,6 @@ from app.services import storagefrom app.services.style_lock import (build_locked_image_prompt,merge_negative,- seedream_ref_urls,strip_lock_blocks,template_allow_source_names,template_consistency_mode,@@ -41,8 +40,10 @@ from app.services.kepu_continuity import (image_refs_for_shot,persist_last_frame_from_video,previous_usable_shot,+ video_image_ref,video_extra_refs_for_shot,)+from app.services.kepu_image_references import project_image_referencesfrom app.services.voices import resolve_speakerfrom app.services import seedance_segments as segplanfrom app.services.bgm import clip_shot_bgm, resolve_bgm_path@@ -186,7 +187,7 @@ def clear_pipeline_cancellation(project_id: int) -> None:def _is_image_text(project: Project) -> bool:- return (project.pipeline_mode or "full") == "image_text"+ return (getattr(project, "pipeline_mode", None) or "full") == "image_text"def _kepu_seedance_native_audio(project: Project | None = None) -> bool:@@ -866,14 +867,6 @@ def _project_image_negative(project: Project) -> str:)-def _project_base_refs(project: Project) -> list[str]:- tpl = project.template- refs = list((tpl.seedream_config or {}).get("ref_images") or []) if tpl else []- if project.ref_image_url:- refs = [project.ref_image_url, *refs]- return seedream_ref_urls(*refs)--def _locked_shot_prompt(project: Project, img_prompt: str) -> str:consist = template_consistency_mode(project.template)return build_locked_image_prompt(@@ -941,7 +934,6 @@ async def _parallel_image_and_audio(project_id: int) -> None:photoreal = template_is_photoreal(tpl)consist = template_consistency_mode(tpl)lock_character = consist == "character"- base_refs = _project_base_refs(project)image_size = _image_size_for(project)negative = _project_image_negative(project)voice = _project_voice(project)@@ -951,11 +943,18 @@ async def _parallel_image_and_audio(project_id: int) -> None:if not shot_meta:return+ # 同步发布参考图可能等待 OSS,必须释放数据库连接后执行。+ base_refs, style_refs = (+ await asyncio.to_thread(project_image_references, project)+ if any(not meta["has_image"] for meta in shot_meta) else ([], [])+ )+img_sem = asyncio.Semaphore(max(1, cfg.pipeline_image_concurrency))done_img = 0progress_lock = asyncio.Lock()# 静图成片仍走外部 TTS;full + Seedance 内置口播则跳过- need_audio = (not _kepu_seedance_native_audio(project)) and (+ native_audio = _kepu_seedance_native_audio(project)+ need_audio = (not native_audio) and (not _continuous_audio_ok(project_id))@@ -975,7 +974,8 @@ async def _parallel_image_and_audio(project_id: int) -> None:project.status = ProjectStatus.IMAGINGawait db.commit()msg = f"出图 {done_img}/{total}" + (- " · 整片配音生成中…" if need_audio else " · 配音已就绪"+ " · 整片配音生成中…" if need_audio else+ " · 声音将在视频阶段生成" if native_audio else " · 配音已就绪")await publish_progress(project_id,@@ -1036,12 +1036,13 @@ async def _parallel_image_and_audio(project_id: int) -> None:size=image_size,model=image_model,aspect_ratio=output_ratio or None,+ style_ref_urls=style_refs or None,)await persist_image(meta, img)from app.services.media_models.runtime import current_snapshotif (current_snapshot.get() or {}).get("mode") != "fixed_media":await _record_seedream_usage(project_id, image_result=img,- model=get_settings().model_image, shot_id=meta["id"])+ model=image_model or get_settings().model_image, shot_id=meta["id"])return SimpleNamespace(image_ark_url=img.remote_url, image_url=img.local_url)async def run_images() -> None:@@ -1055,7 +1056,7 @@ async def _parallel_image_and_audio(project_id: int) -> None:)await bump_images()continue- refs = image_refs_for_shot(prev_proxy, base_refs)+ refs = await asyncio.to_thread(image_refs_for_shot, prev_proxy, base_refs)proxy = await one_image(meta, refs)if proxy:prev_proxy = proxy@@ -1128,7 +1129,7 @@ async def _parallel_image_and_audio(project_id: int) -> None:"stage": "ASSETS_READY","percent": 70 if image_text else 50,"message": (- "分镜图与整片配音已完成"+ "分镜图已完成,下一步生成视频与声音" if native_audio else "分镜图与整片配音已完成"),},)@@ -1169,7 +1170,7 @@ async def _parallel_videos(project_id: int) -> None:"video_prompt": s.video_prompt,"segment_script": getattr(s, "segment_script", "") or s.video_prompt or "","camera": s.camera,- "image_ref": s.image_ark_url or s.image_url or "",+ "image_ref": video_image_ref(s),"image_ark_url": s.image_ark_url,"image_url": s.image_url,"last_frame_url": getattr(s, "last_frame_url", None),@@ -1594,14 +1595,18 @@ async def regen_shot_image(project_id: int, shot_id: int) -> None:shot = next((s for s in project.shots if s.id == shot_id), None)if not shot:raise ValueError("shot not found")- # 生成前先备好参考,避免长等待占着同一条 DB 连接+ # 先读齐元数据;参考图发布与模型请求都在数据库连接释放后进行。shot_no = shot.shot_no- ref_urls = image_refs_for_shot(previous_usable_shot(list(project.shots), shot_no), _project_base_refs(project))+ shot_rows = list(project.shots)negative = _project_image_negative(project)prompt = _locked_shot_prompt(project, shot.img_prompt)image_size = _image_size_for(project)image_model = (getattr(project, "image_model", None) or "").strip()aspect_ratio = _project_output_ratio(project) or None+ base_refs, style_refs = await asyncio.to_thread(project_image_references, project)+ ref_urls = await asyncio.to_thread(+ lambda: image_refs_for_shot(previous_usable_shot(shot_rows, shot_no), base_refs)+ )img = await ark.gen_image(prompt,negative,@@ -1611,6 +1616,7 @@ async def regen_shot_image(project_id: int, shot_id: int) -> None:size=image_size,model=image_model,aspect_ratio=aspect_ratio,+ style_ref_urls=style_refs or None,)cancelled = Falseasync with AsyncSessionLocal() as db:@@ -1635,7 +1641,7 @@ async def regen_shot_image(project_id: int, shot_id: int) -> None:await _record_seedream_usage(project_id,image_result=img,- model=s.model_image,+ model=image_model or s.model_image,shot_id=shot_id,delivered=not cancelled,)@@ -1685,7 +1691,7 @@ async def regen_shot_video(project_id: int, shot_id: int) -> None:hi=cfg.seedance_duration_max,)shot_no = shot.shot_no- image_ref = shot.image_ark_url or shot.image_url or ""+ image_ref = video_image_ref(shot)extra_refs = video_extra_refs_for_shot(previous_usable_shot(list(project.shots), shot_no))video_model = (getattr(project, "video_model", None) or "").strip()ratio = _project_output_ratio(project) or cfg.ark_video_ratiodiff --git a/backend/tests/test_kepu_full_media_e2e.py b/backend/tests/test_kepu_full_media_e2e.pynew file mode 100644index 0000000..cab62dd--- /dev/null+++ b/backend/tests/test_kepu_full_media_e2e.py@@ -0,0 +1,140 @@+"""离线完整模式验收:参考图生图 → 图片生有声视频 → 真正的 FFmpeg 成片。"""+from __future__ import annotations++import json+import shutil+import subprocess+from contextlib import asynccontextmanager+from types import SimpleNamespace+from unittest.mock import AsyncMock, Mock++import httpx+import pytest++from app.config import get_settings+from app.models import Project, ProjectStatus, Shot, ShotStatus+from app.services import ffmpeg_compose, pipeline, storage+++def _run(command):+ """运行本机媒体工具;失败时保留简短诊断。"""+ result = subprocess.run(command, capture_output=True, text=True, encoding="utf-8", errors="replace", timeout=60)+ assert result.returncode == 0, result.stderr[-3000:]+ return result.stdout+++async def test_full_reference_images_to_native_audio_videos_and_playable_vertical_final(monkeypatch, tmp_path):+ """全链路保留画风/主体/镜间参考;素材、音轨和成片均为临时目录内真实文件。"""+ settings = get_settings()+ ffmpeg = shutil.which(settings.ffmpeg_path) or shutil.which("ffmpeg")+ ffprobe = shutil.which(settings.ffprobe_path) or shutil.which("ffprobe")+ if not ffmpeg or not ffprobe or not ffmpeg_compose._find_cjk_font():+ pytest.skip("real full-media acceptance requires FFmpeg, ffprobe and a Chinese font")+ for key, value in {"ark_mock": True, "kepu_seedance_native_audio": True, "ffmpeg_path": ffmpeg,+ "ffprobe_path": ffprobe, "public_base_url": "https://media.example.com"}.items():+ monkeypatch.setattr(settings, key, value)+ monkeypatch.setattr(storage, "STATIC_ROOT", tmp_path / "static")+ monkeypatch.setattr(storage, "GENERATED_ROOT", tmp_path / "static/generated")+ monkeypatch.setattr("app.services.oss.oss_enabled", lambda: False)+ network = AsyncMock(side_effect=AssertionError("full-media acceptance must stay offline"))+ monkeypatch.setattr(httpx.AsyncClient, "send", network)+ monkeypatch.setattr(pipeline, "resolve_bgm_path", lambda _mood: None)+ monkeypatch.setattr(pipeline, "_ensure_not_cancelled", AsyncMock())+ for name in ("publish_progress", "_record_seedream_usage", "_record_seedance_usage"):+ monkeypatch.setattr(pipeline, name, AsyncMock())+ external_tts = AsyncMock(side_effect=AssertionError("native-audio mode must not synthesize external TTS"))+ monkeypatch.setattr(pipeline, "_synthesize_continuous_audio", external_tts)++ style = storage.project_dir(98784) / "style.png"+ _run([ffmpeg, "-y", "-f", "lavfi", "-i", "testsrc2=size=144x256:rate=1", "-frames:v", "1", str(style)])+ style_url = storage.publish_local(style)+ template = SimpleNamespace(+ id="anim_3d", style_prefix="统一三维卡通画风", preview_cover=style_url, negative_prompt="模糊",+ seedream_config={"consistency_mode": "character"}, seedance_config={"character_consistency": True},+ audio_config={}, subtitle_config={}, default_ratio="9:16",+ )+ shots = [SimpleNamespace(+ id=no, shot_no=no, duration=4, narration=text, img_prompt="三维角色观察天空",+ video_prompt="@duration:4 同一个角色讲解", segment_script="@duration:4 同一个角色讲解",+ image_url=None, image_ark_url=None, audio_url=None, video_url=None, last_frame_url=None,+ video_skip_reason=None, camera="push-in", bgm_mood="", status=ShotStatus.PENDING,+ ) for no, text in enumerate(("阳光遇到空气。", "天空呈现蓝色。"), 1)]+ subject = storage.to_public_url(style_url)+ project = SimpleNamespace(+ id=98784, user_id=1, pipeline_mode="full", template=template, shots=shots,+ ref_image_url=subject, character_bible="同一个三维卡通角色", style_prompt="统一三维卡通画风",+ voice_id="", image_model="seedream-5.0-pro", video_model="seedance-2.5", image_resolution="2K",+ video_resolution="720p", output_ratio="9:16", resolution_mode="preview", progress=15,+ status=ProjectStatus.SCRIPT_READY, final_video_url=None,+ )+ db = SimpleNamespace(execute=AsyncMock(return_value=SimpleNamespace(scalar_one=lambda: project)),+ commit=AsyncMock(), add=Mock())++ async def get_row(model, row_id):+ """持久化替身仅回读本用例的项目与分镜。"""+ return project if model is Project else next(shot for shot in shots if shot.id == row_id)++ @asynccontextmanager+ async def session():+ """隔离数据库,同时让实际阶段逻辑写回同一组素材。"""+ yield db++ db.get = AsyncMock(side_effect=get_row)+ monkeypatch.setattr(pipeline, "AsyncSessionLocal", session)+ image_inputs, video_inputs = [], []++ async def image(prompt, negative, refs, **kwargs):+ """本地图片替代生图模型,并记录画风、主体和镜间参考。"""+ image_inputs.append((prompt, refs, kwargs))+ path = storage.project_dir(project.id) / f"frame_{kwargs['shot_no']}.png"+ shutil.copyfile(style, path)+ return SimpleNamespace(local_url=storage.publish_local(path), remote_url=None)++ async def video(image_ref, prompt, duration, **kwargs):+ """从本镜静帧做缩放动画并合成有声音轨,替代云端图生视频。"""+ video_inputs.append((image_ref, kwargs))+ path = storage.project_dir(project.id) / f"video_{kwargs['shot_no']}.mp4"+ _run([ffmpeg, "-y", "-loop", "1", "-framerate", "12", "-i", str(storage.local_path_from_url(image_ref)),+ "-f", "lavfi", "-i", f"sine=frequency={440 + kwargs['shot_no'] * 100}:sample_rate=24000",+ "-vf", "zoompan=z='min(zoom+0.004,1.5)':d=1:s=144x256:fps=12", "-t", str(duration),+ "-c:v", "libx264", "-preset", "ultrafast", "-pix_fmt", "yuv420p", "-c:a", "aac", str(path)])+ tail = path.with_name(f"tail_{kwargs['shot_no']}.png")+ _run([ffmpeg, "-y", "-sseof", "-0.1", "-i", str(path), "-frames:v", "1", str(tail)])+ return storage.publish_local(path), SimpleNamespace(last_frame_url=storage.publish_local(tail))++ gateway = SimpleNamespace(gen_image=image, gen_and_wait_video=video,+ tts=AsyncMock(side_effect=AssertionError("external TTS forbidden")))+ monkeypatch.setattr(pipeline, "get_ark", lambda: gateway)++ await pipeline._parallel_image_and_audio(project.id)+ assert project.status == ProjectStatus.IMAGE_READY+ assert all(call[2]["style_ref_urls"] == [style_url] for call in image_inputs)+ assert all(subject in call[1] and "三维卡通" in call[0] for call in image_inputs)+ assert storage.to_public_url(shots[0].image_url) in image_inputs[1][1]+ await pipeline._parallel_videos(project.id)+ assert project.status == ProjectStatus.VIDEO_READY+ assert [storage.local_path_from_url(call[0]) for call in video_inputs] == [+ storage.local_path_from_url(shot.image_url) for shot in shots+ ]+ assert all(call[1]["generate_audio"] is True for call in video_inputs)+ assert video_inputs[1][1]["extra_image_urls"] == [shots[0].last_frame_url]+ await pipeline._compose_stage(project.id)++ final = storage.local_path_from_url(project.final_video_url)+ assert project.status == ProjectStatus.DONE and final.is_file() and final.stat().st_size > 2000+ probe = json.loads(_run([ffprobe, "-v", "error", "-show_streams", "-show_format", "-of", "json", str(final)]))+ visual = next(stream for stream in probe["streams"] if stream["codec_type"] == "video")+ audio = next(stream for stream in probe["streams"] if stream["codec_type"] == "audio")+ assert visual["codec_name"] == "h264" and audio["codec_name"] == "aac"+ assert visual["width"] * 16 == visual["height"] * 9+ assert 7.8 <= float(probe["format"]["duration"]) <= 8.5+ assert abs(float(visual["duration"]) - float(audio["duration"])) < 0.2+ assert not ffmpeg_compose.is_near_silent_audio(final)+ frames = _run([ffmpeg, "-v", "error", "-i", str(final), "-an", "-vf", "select='eq(n,0)+eq(n,25)'",+ "-fps_mode", "vfr", "-frames:v", "2", "-f", "framemd5", "-"])+ hashes = [line.rsplit(",", 1)[1].strip() for line in frames.splitlines() if line and not line.startswith("#")]+ assert len(hashes) == 2 and hashes[0] != hashes[1]+ assert all(shot.audio_url is None for shot in shots)+ external_tts.assert_not_awaited()+ gateway.tts.assert_not_awaited()+ network.assert_not_awaited()diff --git a/backend/tests/test_kepu_image_references.py b/backend/tests/test_kepu_image_references.pynew file mode 100644index 0000000..c59f927--- /dev/null+++ b/backend/tests/test_kepu_image_references.py@@ -0,0 +1,232 @@+"""短视频生图始终携带画风参考,并保留用户和镜间参考。"""+from types import SimpleNamespace+from contextlib import asynccontextmanager+from unittest.mock import AsyncMock++import pytest++from app.config import get_settings+from app.services import storage+from app.models import Project, ProjectStatus, Shot, ShotStatus, Template+from app.services import pipeline+from app.services.ark import ArkGateway+from app.models_tasks import TaskRun+from app.services.media_models import MediaValidationError, get_strategy, planning+from app.services.kepu_image_references import (+ project_image_reference_inputs,+ project_image_references,+ public_image_reference,+)+++def _project(**overrides):+ """构造具有默认画风封面的短视频项目。"""+ data = {"template": SimpleNamespace(seedream_config={}, preview_cover="/static/templates/covers/anim_3d.png"),+ "ref_image_url": None}+ return SimpleNamespace(**{**data, **overrides})+++def real_references(monkeypatch, tmp_path):+ """使用本地媒体和公网地址模拟真实参考图发布,不访问网络。"""+ settings = get_settings()+ monkeypatch.setattr(settings, "ark_mock", False)+ monkeypatch.setattr(settings, "local_media_mock", False)+ monkeypatch.setattr(settings, "public_base_url", "https://media.example.com")+ monkeypatch.setattr(storage, "STATIC_ROOT", tmp_path)+ monkeypatch.setattr(storage, "republish_url", lambda url, **_: url)+ cover = tmp_path / "templates/covers/anim_3d.png"+ cover.parent.mkdir(parents=True)+ cover.write_bytes(b"reference image")+ return tmp_path+++def test_first_shot_gets_template_cover_as_dedicated_style_reference(real_references):+ """模板没配 ref_images 时仍以所选画风封面作参考。"""+ subjects, styles = project_image_references(_project())+ assert subjects == []+ assert styles == ["https://media.example.com/static/templates/covers/anim_3d.png"]+++def test_builtin_legacy_empty_cover_uses_bundled_style_board(real_references):+ """旧模板行封面为空时,内置画风仍使用随代码发布的参考图。"""+ project = _project(template=SimpleNamespace(id="anim_3d", preview_cover="", seedream_config={}))+ assert project_image_references(project)[1] == ["https://media.example.com/static/templates/covers/anim_3d.png"]+++def test_user_reference_does_not_replace_style_reference(real_references):+ """用户图用于主体,画风图独立保留。"""+ subjects, styles = project_image_references(_project(ref_image_url="https://media.example.com/person.png"))+ assert subjects == ["https://media.example.com/person.png"]+ assert styles == ["https://media.example.com/static/templates/covers/anim_3d.png"]+++def test_configured_style_board_takes_priority_over_cover(real_references):+ """后台配置的画风参考优先于展示封面。"""+ project = _project(template=SimpleNamespace(+ seedream_config={"style_ref_urls": ["https://media.example.com/style.png"]},+ preview_cover="/static/templates/covers/anim_3d.png"))+ assert project_image_references(project)[1] == ["https://media.example.com/style.png"]+++def test_legacy_subject_images_are_preserved_alongside_explicit_style_board(real_references):+ """新增画风槽位不能吞掉旧模板的角色与产品参考。"""+ project = _project(template=SimpleNamespace(+ seedream_config={"ref_images": ["https://media.example.com/person.png", "https://media.example.com/product.png"],+ "style_ref_urls": ["https://media.example.com/style.png"]}, preview_cover=""))+ assert project_image_references(project) == (+ ["https://media.example.com/person.png", "https://media.example.com/product.png"],+ ["https://media.example.com/style.png"],+ )+++def test_local_reference_prefers_synchronous_publishing(real_references, monkeypatch):+ """中间图显式同步发布,不能把本地 URL 直接交给云端。"""+ published = []+ def publish(url, *, sync):+ """模拟 OSS 发布。"""+ published.append((url, sync))+ return "https://oss.example.com/style.png"+ monkeypatch.setattr(storage, "republish_url", publish)+ assert project_image_references(_project())[1] == ["https://oss.example.com/style.png"]+ assert published == [("/static/templates/covers/anim_3d.png", True)]+++def test_inaccessible_style_fails_instead_of_silently_using_text_only(real_references, monkeypatch):+ """真实生成没有可访问参考图时,明确失败而非退回纯提示词。"""+ monkeypatch.setattr(get_settings(), "public_base_url", "http://127.0.0.1:8000")+ with pytest.raises(ValueError, match="画风参考图"):+ project_image_references(_project())+++def test_local_reference_cannot_fall_back_to_metadata_server(real_references, monkeypatch):+ """本地图片转绝对地址时同样拒绝私网地址。"""+ monkeypatch.setattr(get_settings(), "public_base_url", "https://169.254.169.254")+ assert public_image_reference("/static/templates/covers/anim_3d.png") is None+++async def test_video_gateway_accepts_public_local_image_without_oss(real_references):+ """图生视频与生图共用可访问的本地图,无 OSS 时也可使用公网 HTTPS 地址。"""+ gateway = object.__new__(ArkGateway)+ assert await gateway._resolve_image_ref("/static/templates/covers/anim_3d.png", prefer_https=True) == (+ "https://media.example.com/static/templates/covers/anim_3d.png"+ )+++async def test_video_gateway_rejects_local_only_reference(real_references, monkeypatch):+ """云端无法读取本机图片时,在提交付费请求前报错。"""+ monkeypatch.setattr(get_settings(), "public_base_url", "http://127.0.0.1:8000")+ gateway = object.__new__(ArkGateway)+ with pytest.raises(RuntimeError, match="公网可访问"):+ await gateway._resolve_image_ref("/static/templates/covers/anim_3d.png", prefer_https=True)+++def test_mock_reference_does_not_publish_or_require_media_files(monkeypatch):+ """离线生成允许本地画风图,不触发 OSS 或 HTTP。"""+ monkeypatch.setattr(get_settings(), "ark_mock", True)+ monkeypatch.setattr(storage, "republish_url", lambda *_args, **_kwargs: pytest.fail("mock must not upload"))+ assert project_image_references(_project())[1] == ["/static/templates/covers/anim_3d.png"]+++def test_admission_reads_reference_slots_without_publishing(monkeypatch):+ """预占阶段仅采集引用,不上传也不发模型请求。"""+ monkeypatch.setattr(storage, "republish_url", lambda *_args, **_kwargs: pytest.fail("admission must not upload"))+ subjects, styles = project_image_reference_inputs(_project(ref_image_url="/static/person.png"))+ assert subjects == ["/static/person.png"]+ assert styles == ["/static/templates/covers/anim_3d.png"]++[email protected]("url", [+ "https://www.tokenfree.com/v1/tasks/t1/artifacts/image-0/content",+ "/static/../secret.png", "file:///private/image.png", "https://127.0.0.1/style.png",+ "https://169.254.169.254/style.png", "https://127.0.0.2/style.png",+])+def test_reference_rejects_private_provider_or_unsafe_sources(real_references, url):+ """鉴权产物地址、本地越界路径与私网地址不能泄给下游。"""+ assert public_image_reference(url) is None++[email protected]("regenerate", [False, True], ids=["batch", "single-redraw"])+async def test_image_generation_receives_fixed_style_and_previous_subject(real_references, monkeypatch, regenerate):+ """批量生成与单镜重绘都真实向网关传入固定画风、用户图和上一镜图。"""+ template = Template(id="anim_3d", name="3D 动画", style_prefix="圆润三维动画",+ preview_cover="/static/templates/covers/anim_3d.png", seedream_config={},+ seedance_config={}, audio_config={})+ shots = [Shot(id=no, shot_no=no, img_prompt=f"同一角色观察天空 {no}", duration=5,+ status=ShotStatus.PENDING, version=1) for no in (1, 2)]+ project = Project(id=991, user_id=1, template_id=template.id, template=template,+ pipeline_mode="full", output_ratio="9:16", image_model="seedream-5.0-pro",+ image_resolution="2K", ref_image_url="https://media.example.com/character.png",+ character_bible="蓝色外套的男孩", shots=shots, status=ProjectStatus.SCRIPT_READY)+ db = SimpleNamespace(execute=AsyncMock(return_value=SimpleNamespace(scalar_one=lambda: project)),+ commit=AsyncMock())++ async def get_row(model, row_id):+ """回读当前项目和分镜。"""+ return project if model is Project else next((shot for shot in shots if shot.id == row_id), None)++ @asynccontextmanager+ async def sessions():+ """离线数据库替身。"""+ yield db++ async def gen_image(_prompt, _negative, _refs, **kwargs):+ """保存图片以供下一镜参考,无模型或网络调用。"""+ path = storage.project_dir(project.id) / f"shot_{kwargs['shot_no']}.png"+ path.write_bytes(b"generated image")+ return SimpleNamespace(local_url=storage.rel_static_url(path),+ remote_url="https://www.tokenfree.com/v1/tasks/t1/artifacts/image-0/content")++ generate = AsyncMock(side_effect=gen_image)+ db.get = AsyncMock(side_effect=get_row)+ monkeypatch.setattr(storage, "GENERATED_ROOT", real_references / "generated")+ monkeypatch.setattr(get_settings(), "kepu_seedance_native_audio", True)+ monkeypatch.setattr(pipeline, "AsyncSessionLocal", sessions)+ monkeypatch.setattr(pipeline, "get_ark", lambda: SimpleNamespace(gen_image=generate))+ for method in ("_ensure_not_cancelled", "_set_status", "publish_progress", "_record_seedream_usage"):+ monkeypatch.setattr(pipeline, method, AsyncMock())+ if regenerate:+ shots[0].image_url = "https://media.example.com/previous.png"+ shots[1].video_url = "/static/old.mp4"+ project.final_video_url = "/static/old-final.mp4"+ await pipeline.regen_shot_image(project.id, shots[1].id)+ calls = generate.await_args_list+ assert calls[0].args[2] == [shots[0].image_url, project.ref_image_url]+ assert shots[1].video_url is None and project.final_video_url is None+ else:+ await pipeline._parallel_image_and_audio(project.id)+ calls = generate.await_args_list+ assert len(calls) == 2+ assert calls[0].args[2] == [project.ref_image_url]+ assert calls[1].args[2] == ["https://media.example.com/static/generated/p991/shot_1.png", project.ref_image_url]+ for call in calls:+ assert call.kwargs["style_ref_urls"] == ["https://media.example.com/static/templates/covers/anim_3d.png"]+ assert call.kwargs["model"] == project.image_model+ assert "三维" in call.args[0] and "蓝色外套" in call.args[0]++[email protected]("reference_cap", [3, 2])+async def test_image_admission_reserves_style_subject_and_previous_slots_without_upload(monkeypatch, reference_cap):+ """图片引用数量在受理时核验,后镜必需的画风名额不能被忽略。"""+ template = SimpleNamespace(id="anim_3d", seedream_config={}, preview_cover="/static/style.png")+ shots = [SimpleNamespace(id=no, shot_no=no, image_url=None, image_ark_url=None) for no in (1, 2)]+ project = SimpleNamespace(id=1, template=template, ref_image_url="/static/subject.png", shots=shots,+ image_model="seedream-5.0-pro", image_resolution="2K", output_ratio="9:16")+ db = SimpleNamespace(execute=AsyncMock(return_value=SimpleNamespace(scalar_one_or_none=lambda: project)))+ strategy = get_strategy("seedream-5.0-pro").with_reference_limits({"images": reference_cap, "videos": 0, "audios": 0})+ monkeypatch.setattr(planning, "resolve_strategy", lambda *_: strategy)+ monkeypatch.setattr(planning, "pin_route", lambda *_: {})+ monkeypatch.setattr(storage, "republish_url", lambda *_args, **_kwargs: pytest.fail("admission must not upload"))+ task = TaskRun(domain="kepu", task_type="project_pipeline", project_id=1, payload={"phase": "assets"})+ if reference_cap == 2:+ with pytest.raises(MediaValidationError, match="参考图片"):+ await planning.plan_items(db, task)+ return+ items = await planning.plan_items(db, task)+ assert items[0]["params"]["reference_images"] == ["/static/subject.png"]+ assert items[1]["params"]["reference_images"] == ["pending://shot-1-image", "/static/subject.png"]+ assert all(item["params"]["style_ref_urls"] == ["/static/style.png"] for item in items)diff --git a/backend/tests/test_kepu_video_media_planning.py b/backend/tests/test_kepu_video_media_planning.pynew file mode 100644index 0000000..e132e9a--- /dev/null+++ b/backend/tests/test_kepu_video_media_planning.py@@ -0,0 +1,171 @@+"""Short-video admission reserves the same video request as the worker, offline."""+from types import SimpleNamespace+from unittest.mock import AsyncMock, Mock++import httpx+import pytest++from app.config import get_settings+from app.models_tasks import TaskRun+from app.services import pipeline, storage+from app.services.media_models import planning, runtime+++def _shot(no, **changes):+ return SimpleNamespace(**{+ "id": no, "shot_no": no, "duration": 5, "segment_script": "",+ "video_prompt": "", "image_url": f"/static/generated/p1/shot_{no:03d}.png",+ "image_ark_url": None, "video_url": None, "last_frame_url": None,+ "video_skip_reason": None, **changes,+ })+++def _project(shots, **changes):+ return SimpleNamespace(**{+ "id": 1, "pipeline_mode": "full", "image_model": "seedream-5.0-pro",+ "video_model": "seedance-2.5", "output_ratio": "9:16", "resolution_mode": "sd",+ "video_resolution": "720p", "template": None, "shots": shots, **changes,+ })+++def _db(project):+ return SimpleNamespace(execute=AsyncMock(return_value=Mock(scalar_one_or_none=lambda: project)))+++def _task(kind="project_pipeline", **changes):+ return TaskRun(domain="kepu", task_type=kind, project_id=1, payload={"phase": "videos"}, **changes)+++def offline(monkeypatch):+ settings = get_settings()+ monkeypatch.setattr(settings, "seedance_duration_min", 4)+ monkeypatch.setattr(settings, "seedance_duration_max", 30)+ monkeypatch.setattr(settings, "kepu_seedance_native_audio", True)+ monkeypatch.setattr(settings, "kepu_seedance_sfx_audio", False)+ monkeypatch.setattr(planning, "pin_route", lambda capability, model: {+ "capability": capability, "logical_model_id": model, "upstream_model": model,+ "channel_id": "__runtime__", "channel_name": "Runtime", "base_url": settings.ark_base_url,+ "protocol": "openai", "api_format": "openai",+ })+ forbidden = Mock(side_effect=AssertionError("admission must not generate or publish media"))+ monkeypatch.setattr(storage, "publish_local", forbidden)+ monkeypatch.setattr(storage, "republish_url", forbidden)+ monkeypatch.setattr(pipeline, "get_ark", forbidden)+ network = AsyncMock(side_effect=AssertionError("admission must stay offline"))+ monkeypatch.setattr(httpx.AsyncClient, "send", network)+ return forbidden, network+++async def test_video_snapshot_pins_script_duration_audio_and_output_settings(offline, monkeypatch):+ shot = _shot(1, duration=5, segment_script="@duration:4 观察天空\n@duration:6 解释散射")+ project = _project([shot], output_ratio="16:9", video_resolution="1080p")+ task = _task()+ monkeypatch.setattr(planning, "active_book", AsyncMock(return_value=None))+ await planning.prepare_task_media(_db(project), task)+ saved = task.billing_snapshot["items"][0]+ assert saved["params"]["duration"] == 10+ assert saved["params"]["generate_audio"] is True+ assert saved["params"]["resolution"] == "1080p"+ assert saved["params"]["aspect_ratio"] == "16:9"+ token = runtime.current_snapshot.set(task.billing_snapshot)+ op_token = runtime.current_operation.set(None)+ try:+ _, actual, _ = runtime.execution_params("video", {+ "duration": 5, "resolution": "480p", "aspect_ratio": "9:16",+ "generate_audio": True, "reference_images": [shot.image_url],+ }, shot_no=1, model=project.video_model)+ assert actual["duration"] == 10+ assert actual["resolution"] == "1080p" and actual["aspect_ratio"] == "16:9"+ finally:+ runtime.current_snapshot.reset(token)+ runtime.current_operation.reset(op_token)+ offline[0].assert_not_called()+ offline[1].assert_not_awaited()++[email protected]("changes,expected", [+ ({"video_prompt": "@duration:6 第一段\n@duration:6 第二段"}, 12),+ ({"duration": 2}, 4),+ ({"duration": 80}, 30),+ ({"duration": 8.4}, 8),+])+async def test_video_snapshot_uses_legacy_script_and_worker_fallback_clamp(offline, changes, expected):+ items = await planning.plan_items(_db(_project([_shot(1, **changes)])), _task())+ assert items[0]["params"]["duration"] == expected++[email protected]("native,sfx,expected", [(True, False, True), (False, True, True), (False, False, False)])+async def test_video_snapshot_tracks_native_and_effect_audio(offline, monkeypatch, native, sfx, expected):+ monkeypatch.setattr(get_settings(), "kepu_seedance_native_audio", native)+ monkeypatch.setattr(get_settings(), "kepu_seedance_sfx_audio", sfx)+ items = await planning.plan_items(_db(_project([_shot(1)])), _task())+ assert items[0]["params"]["generate_audio"] is expected+++async def test_video_references_prefer_saved_image_and_reserve_generated_previous_tail(offline):+ first = _shot(1, image_ark_url="https://www.tokenfree.com/v1/tasks/t1/artifacts/image-0/content")+ second = _shot(2)+ items = await planning.plan_items(_db(_project([second, first])), _task())+ assert [item["shot_no"] for item in items] == [1, 2]+ assert items[0]["params"]["reference_images"] == [first.image_url]+ refs = items[1]["params"]["reference_images"]+ assert refs[0] == second.image_url and len(refs) == 2+ assert refs[1].startswith("pending://")+ assert not any("tokenfree.com" in ref for item in items for ref in item["params"]["reference_images"])+ offline[0].assert_not_called()+++async def test_video_references_reuse_ready_previous_tail_without_regenerating_it(offline):+ first = _shot(1, video_url="/static/generated/p1/shot_001.mp4", last_frame_url="/static/generated/p1/tail.jpg")+ second = _shot(2)+ items = await planning.plan_items(_db(_project([first, second])), _task())+ assert len(items) == 1+ assert items[0]["params"]["reference_images"] == [second.image_url, first.last_frame_url]+++async def test_video_references_reserve_frame_extraction_without_reading_existing_video(offline):+ first = _shot(1, video_url="/static/generated/p1/shot_001.mp4")+ second = _shot(2)+ items = await planning.plan_items(_db(_project([first, second])), _task())+ assert len(items) == 1+ refs = items[0]["params"]["reference_images"]+ assert refs[0] == second.image_url and len(refs) == 2 and refs[1].startswith("pending://")+ offline[0].assert_not_called()+++async def test_video_references_never_snapshot_tokenfree_authenticated_urls(offline):+ private = "https://www.tokenfree.com/v1/tasks/t1/artifacts/image-0/content"+ first = _shot(1, image_url=private, image_ark_url="https://cdn.example.com/first.png")+ second = _shot(2, image_url=private, image_ark_url=private)+ items = await planning.plan_items(_db(_project([first, second])), _task())+ assert items[0]["params"]["reference_images"] == [first.image_ark_url]+ assert items[1]["params"]["reference_images"][0].startswith("pending://")+ assert not any("tokenfree.com" in ref for item in items for ref in item["params"]["reference_images"])+++async def test_video_regen_reserves_prior_usable_still_and_replaces_only_requested_shot(offline):+ first = _shot(1, video_skip_reason="privacy", image_ark_url="https://www.tokenfree.com/v1/tasks/t1/artifacts/image-0/content")+ empty = _shot(2, image_url=None)+ third = _shot(3, video_url="/static/generated/p1/old.mp4")+ items = await planning.plan_items(_db(_project([third, empty, first])), _task("shot_regen_video", shot_id=3))+ assert len(items) == 1 and items[0]["target_id"] == 3+ assert items[0]["params"]["reference_images"] == [third.image_url, first.image_url]+++async def test_video_reference_cap_rejected_before_provider_or_publication(offline, monkeypatch):+ base_resolve = planning.resolve_strategy+ monkeypatch.setattr(planning, "resolve_strategy", lambda model: base_resolve(model).with_reference_limits({"images": 1, "audios": 0, "videos": 0}))+ with pytest.raises(ValueError, match="reference_images"):+ await planning.plan_items(_db(_project([_shot(1), _shot(2)])), _task())+ offline[0].assert_not_called()+ offline[1].assert_not_awaited()diff --git a/backend/tests/test_kepu_video_workflow.py b/backend/tests/test_kepu_video_workflow.pynew file mode 100644index 0000000..2614918--- /dev/null+++ b/backend/tests/test_kepu_video_workflow.py@@ -0,0 +1,330 @@+"""分步短视频模式的阶段、模式切换与单镜生成契约(全程离线)。"""+from __future__ import annotations++from contextlib import asynccontextmanager+from types import SimpleNamespace+from unittest.mock import AsyncMock++import pytest+from fastapi import HTTPException+from sqlalchemy import select++from app.api import projects+from app.config import get_settings+from app.models import Project, ProjectStatus, Shot, ShotStatus, Template+from app.models_tasks import TaskRun+from app.schemas import ProjectCreate, ProjectUpdate+from app.services import pipeline+from app.services.billing.settlement import freeze_for_task+from app.services.media_models.prices import active_book, publish_book+from tests.conftest import make_user+++def _shot(**overrides):+ """构造已有首帧、尚未生成视频的分镜。"""+ values = dict(+ id=11, shot_no=1, duration=8, narration="同一个三维卡通角色观察天空。",+ img_prompt="三维卡通角色", image_url="/static/shot.png", image_ark_url=None,+ audio_url=None, video_url=None, last_frame_url=None, video_skip_reason=None,+ video_prompt="@duration:8 缓慢推近", segment_script="@duration:8 缓慢推近",+ camera="push-in", status=ShotStatus.IMAGE_READY, version=1,+ )+ return SimpleNamespace(**{**values, **overrides})+++def _project(**overrides):+ """构造可编辑的分步项目并保留模板生成参数。"""+ values = dict(+ id=1, user_id=7, creation_session_id=None, pipeline_mode="full",+ status=ProjectStatus.DONE, progress=100, final_video_url="/static/final.mp4",+ error_msg=None, active_tasks=[], shots=[_shot()], output_ratio="9:16",+ resolution_mode="hd", image_resolution="2K", video_resolution="720p",+ style_prompt="统一三维卡通画风", video_model="seedance-2-5",+ template=SimpleNamespace(style_prefix="三维卡通", default_ratio="16:9",+ seedance_config={"motion_bias": "平稳", "character_consistency": True}),+ )+ return SimpleNamespace(**{**values, **overrides})+++def _api_context(monkeypatch, project):+ """隔离拥有者查询与数据库提交,仅记录实际路由创建的任务。"""+ monkeypatch.setattr(projects, "_get_owned_project", AsyncMock(return_value=project))+ db = SimpleNamespace(commit=AsyncMock(), rollback=AsyncMock())+ user = SimpleNamespace(id=project.user_id)+ return db, user++[email protected]("before,after,ready_audio,expected", [+ ("image_text", "full", False, ProjectStatus.IMAGE_READY),+ ("full", "image_text", False, ProjectStatus.SCRIPT_READY),+ ("full", "image_text", True, ProjectStatus.VIDEO_READY),+])+async def test_mode_change_invalidates_final_and_resolves_new_stage(+ monkeypatch, before, after, ready_audio, expected,+):+ """切换制作模式沿用已有素材,但成片与就绪状态必须按新模式重算。"""+ project = _project(pipeline_mode=before)+ image = project.shots[0].image_url+ monkeypatch.setattr(get_settings(), "kepu_seedance_native_audio", True)+ monkeypatch.setattr("app.services.kepu_stages.continuous_narration_ok", lambda _id: ready_audio)+ monkeypatch.setattr("app.services.kepu_stages.shot_audio_file_ok", lambda _shot: ready_audio)+ db, user = _api_context(monkeypatch, project)++ updated = await projects.update_project(project.id, ProjectUpdate(pipeline_mode=after), db, user)++ assert updated.pipeline_mode == after+ assert updated.final_video_url is None+ assert updated.status == expected+ assert updated.shots[0].image_url == image+ db.commit.assert_awaited_once()+++async def test_unchanged_mode_preserves_completed_output(monkeypatch):+ """重复保存同一模式不会让已完成作品失效。"""+ project = _project()+ db, user = _api_context(monkeypatch, project)+ await projects.update_project(project.id, ProjectUpdate(pipeline_mode="full"), db, user)+ assert project.status == ProjectStatus.DONE+ assert project.final_video_url == "/static/final.mp4"+++async def test_mode_and_bgm_change_rechecks_new_mode_even_from_image_ready(monkeypatch):+ """素材就绪状态和同时保存的配乐不能掩盖新模式所缺的配音阶段。"""+ project = _project(status=ProjectStatus.IMAGE_READY)+ monkeypatch.setattr("app.services.kepu_stages.continuous_narration_ok", lambda _id: False)+ monkeypatch.setattr("app.services.kepu_stages.shot_audio_file_ok", lambda _shot: False)+ db, user = _api_context(monkeypatch, project)+ await projects.update_project(+ project.id, ProjectUpdate(pipeline_mode="image_text", bgm_lock="轻快"), db, user,+ )+ assert project.pipeline_mode == "image_text" and project.bgm_lock == "轻快"+ assert project.status == ProjectStatus.SCRIPT_READY+ assert project.final_video_url is None+++async def test_mode_change_rejects_active_generation(monkeypatch):+ """视频生成执行期间不能改模式而让计费与实际阶段分离。"""+ project = _project(status=ProjectStatus.VIDEOING)+ db, user = _api_context(monkeypatch, project)+ with pytest.raises(HTTPException) as error:+ await projects.update_project(project.id, ProjectUpdate(pipeline_mode="image_text"), db, user)+ assert error.value.status_code == 409+ assert project.pipeline_mode == "full"+ db.commit.assert_not_awaited()+++async def test_full_generate_routes_script_assets_and_video_before_compose(monkeypatch):+ """完整模式每次只入队一个付费阶段,全部视频就绪后改走专用合成任务。"""+ project = _project(status=ProjectStatus.DRAFT, shots=[], final_video_url=None)+ db, user = _api_context(monkeypatch, project)+ create_task = AsyncMock()+ monkeypatch.setattr(projects, "create_task", create_task)+ monkeypatch.setattr(get_settings(), "kepu_seedance_native_audio", True)+ monkeypatch.setattr(projects, "list_active_tasks_for_owner", AsyncMock(return_value=[]))++ await projects.generate_project(project.id, db=db, user=user)+ assert create_task.await_args.args[2].payload["phase"] == "script"+ assert create_task.await_args.args[2].payload["pipeline_mode"] == "full"+ assert project.status == ProjectStatus.SCRIPTING++ project.status = ProjectStatus.SCRIPT_READY+ project.shots = [_shot(image_url=None)]+ await projects.generate_project(project.id, db=db, user=user)+ assert create_task.await_args.args[2].payload["phase"] == "assets"+ assert project.status == ProjectStatus.IMAGING++ project.status = ProjectStatus.IMAGE_READY+ project.shots[0].image_url = "/static/shot.png"+ await projects.generate_project(project.id, db=db, user=user)+ assert create_task.await_args.args[2].payload["phase"] == "videos"+ assert project.status == ProjectStatus.VIDEOING++ project.status = ProjectStatus.VIDEO_READY+ project.shots[0].video_url = "/static/shot.mp4"+ with pytest.raises(HTTPException, match="409"):+ await projects.generate_project(project.id, db=db, user=user)+ assert create_task.await_count == 3+ await projects.compose_only(project.id, db=db, user=user)+ assert create_task.await_args.args[2].task_type == "project_compose_only"+ assert project.status == ProjectStatus.COMPOSING++[email protected]("mode,has_image,allowed", [+ ("full", True, True), ("full", False, False), ("image_text", True, False),+])+async def test_regen_video_requires_full_mode_and_a_starting_image(monkeypatch, mode, has_image, allowed):+ """视频重生成只允许完整模式、且已有首帧的分镜。"""+ project = _project(pipeline_mode=mode, shots=[_shot(image_url="/static/shot.png" if has_image else None)])+ db, user = _api_context(monkeypatch, project)+ create_task = AsyncMock()+ monkeypatch.setattr(projects, "_create_kepu_task", create_task)+ if allowed:+ await projects.regen_video(project.id, 11, db, user)+ assert create_task.await_args.kwargs["task_type"] == "shot_regen_video"+ assert project.status == ProjectStatus.VIDEOING+ else:+ with pytest.raises(HTTPException) as error:+ await projects.regen_video(project.id, 11, db, user)+ assert error.value.status_code == 400+ create_task.assert_not_awaited()+ db.commit.assert_not_awaited()+++def test_full_create_contract_preserves_user_media_choices():+ """创建参数支持视频模式、参考图、选定的模型和输出清晰度。"""+ request = ProjectCreate(+ template_id="anim_3d", source_text="讲解天空为什么是蓝色。", pipeline_mode="full",+ ref_image_url="/static/reference.png", image_model="gpt-image-1.5", image_resolution="2K",+ video_model="seedance-2-5", video_resolution="720p", target_duration_sec=60,+ )+ assert request.pipeline_mode == "full"+ assert request.ref_image_url == "/static/reference.png"+ assert request.image_model == "gpt-image-1.5" and request.image_resolution == "2K"+ assert request.video_model == "seedance-2-5" and request.video_resolution == "720p"++[email protected]("upstream_image,expected_first_frame", [+ ("https://media.example/start-1.png", "https://media.example/start-1.png"),+ ("https://www.tokenfree.com/v1/tasks/t1/artifacts/image-0/content", "/static/shot.png"),+])+async def test_full_video_generation_uses_own_image_and_previous_tail_with_native_audio(+ monkeypatch, upstream_image, expected_first_frame,+):+ """图生视频沿用本镜首帧、前镜尾帧、脚本时长和项目模型,完整模式保留内置口播。"""+ shot1 = _shot(image_ark_url=upstream_image, duration=3,+ segment_script="@duration:4 观察天空\n@duration:4 蓝光向四周散射")+ shot2 = _shot(id=12, shot_no=2, image_url="/static/start-2.png", duration=6,+ segment_script="@duration:6 同一个角色展示蓝色天空")+ project = _project(shots=[shot2, shot1], final_video_url=None, status=ProjectStatus.IMAGE_READY)+ db = SimpleNamespace(+ execute=AsyncMock(return_value=SimpleNamespace(scalar_one=lambda: project)), commit=AsyncMock(),+ )++ async def get_row(model, row_id):+ """模拟项目与两镜的持久化回读。"""+ return project if model is Project else {shot1.id: shot1, shot2.id: shot2}.get(row_id)++ @asynccontextmanager+ async def session():+ """为每次分镜写回提供同一离线数据库替身。"""+ yield db++ db.get = AsyncMock(side_effect=get_row)+ generate_video = AsyncMock(side_effect=[+ ("/static/video-1.mp4", SimpleNamespace(last_frame_url="/static/tail-1.png")),+ ("/static/video-2.mp4", SimpleNamespace(last_frame_url="/static/tail-2.png")),+ ])+ record_usage = AsyncMock()+ monkeypatch.setattr(get_settings(), "kepu_seedance_native_audio", True)+ monkeypatch.setattr(pipeline, "AsyncSessionLocal", session)+ monkeypatch.setattr(pipeline, "get_ark", lambda: SimpleNamespace(gen_and_wait_video=generate_video))+ monkeypatch.setattr(pipeline, "_ensure_not_cancelled", AsyncMock())+ monkeypatch.setattr(pipeline, "_set_status", AsyncMock())+ monkeypatch.setattr(pipeline, "publish_progress", AsyncMock())+ monkeypatch.setattr(pipeline, "_record_seedance_usage", record_usage)+ monkeypatch.setattr(pipeline, "persist_last_frame_from_video", lambda *args, **kwargs: kwargs.get("preferred_url"))++ await pipeline._parallel_videos(project.id)++ first, second = generate_video.await_args_list+ assert first.args[0] == expected_first_frame+ assert second.args[0] == "/static/start-2.png"+ assert first.args[2] == 8 and second.args[2] == 6+ assert first.kwargs["extra_image_urls"] is None+ assert second.kwargs["extra_image_urls"] == ["/static/tail-1.png"]+ for call in (first, second):+ assert call.kwargs["generate_audio"] is True+ assert call.kwargs["model"] == "seedance-2-5"+ assert call.kwargs["resolution"] == "720p" and call.kwargs["ratio"] == "9:16"+ assert call.kwargs["character_consistency"] is True+ assert "三维卡通" in call.args[1]+ assert shot1.video_url == "/static/video-1.mp4" and shot2.video_url == "/static/video-2.mp4"+ assert project.status == ProjectStatus.VIDEO_READY and project.progress == 88+ assert [call.kwargs["fallback_duration_sec"] for call in record_usage.await_args_list] == [8, 6]+ assert all(call.kwargs["billing_key"] == "seedance2:video0" for call in record_usage.await_args_list)+++async def test_full_project_video_admission_reserves_only_remaining_video_cost(db_session, monkeypatch):+ """真实创建/入队/冻结链路只为尚缺的视频预扣,不重复计入已有视频与图片。"""+ db = db_session+ user = await make_user(db, balance_fen=100_000)+ template = await db.get(Template, "anim_3d")+ if template is None:+ db.add(Template(id="anim_3d", name="3D动画", style_prefix="三维卡通"))+ await db.flush()+ book = await active_book(db)+ await publish_book(+ db, prices={"seedance-2.5": {"720p": "0.5000"}},+ expected_version=book["version"] if book else None, user_id=user.id,+ )+ monkeypatch.setattr(get_settings(), "kepu_seedance_native_audio", True)+ monkeypatch.setattr(get_settings(), "ark_mock", True)+ project = await projects.create_project(ProjectCreate(+ template_id="anim_3d", source_text="讲解天空为什么是蓝色。", pipeline_mode="full",+ video_model="seedance-2.5", video_resolution="720p", output_ratio="9:16",+ ), db, user)+ project.shots = [+ Shot(shot_no=1, duration=8, image_url="/static/first.png", segment_script="@duration:8 观察天空"),+ Shot(shot_no=2, duration=6, image_url="/static/second.png", video_url="/static/kept.mp4"),+ ]+ project.status = ProjectStatus.IMAGE_READY+ await db.commit()++ generated = await projects.generate_project(project.id, db=db, user=user)+ task = (await db.execute(select(TaskRun).where(TaskRun.project_id == project.id))).scalar_one()+ assert generated.pipeline_mode == "full" and generated.status == ProjectStatus.VIDEOING+ assert task.payload["phase"] == "videos"+ assert task.billing_snapshot["mode"] == "fixed_media"+ items = task.billing_snapshot["items"]+ assert len(items) == 1 and items[0]["target_id"] == project.shots[0].id+ assert items[0]["params"]["duration"] == 8+ assert items[0]["model_id"] == "seedance-2.5" and items[0]["params"]["resolution"] == "720p"+ before = user.balance_fen+ reserved = await freeze_for_task(db, task)+ assert reserved == 400+ assert user.balance_fen == before - reserved and user.frozen_fen == reserved+ assert task.billing_status == "frozen"++[email protected]("upstream_image,expected_first_frame", [+ ("https://media.example/start-2.png", "https://media.example/start-2.png"),+ ("https://www.tokenfree.com/v1/tasks/t2/artifacts/image-0/content", "/static/start-2.png"),+])+async def test_single_video_regeneration_preserves_image_duration_and_audio_contract(+ monkeypatch, upstream_image, expected_first_frame,+):+ """单镜重生成使用与批量生成一致的首帧选择、前镜尾帧和内置口播参数。"""+ first = _shot(last_frame_url="/static/previous-tail.png", video_url="/static/kept.mp4")+ shot = _shot(id=12, shot_no=2, duration=3, image_ark_url=upstream_image,+ image_url="/static/start-2.png", segment_script="@duration:9 同一个角色继续讲解")+ project = _project(shots=[first, shot], status=ProjectStatus.VIDEO_READY)+ db = SimpleNamespace(execute=AsyncMock(return_value=SimpleNamespace(scalar_one=lambda: project)),+ commit=AsyncMock())++ async def get_row(model, row_id):+ """为单镜重生成提供对应的项目与分镜。"""+ return project if model is Project else shot++ @asynccontextmanager+ async def session():+ """用内存替身隔离重生成的写回。"""+ yield db++ db.get = AsyncMock(side_effect=get_row)+ generate_video = AsyncMock(return_value=("/static/regenerated.mp4", SimpleNamespace(last_frame_url="/static/new-tail.png")))+ monkeypatch.setattr(get_settings(), "kepu_seedance_native_audio", True)+ monkeypatch.setattr(pipeline, "AsyncSessionLocal", session)+ monkeypatch.setattr(pipeline, "get_ark", lambda: SimpleNamespace(gen_and_wait_video=generate_video))+ monkeypatch.setattr(pipeline, "_record_seedance_usage", AsyncMock())+ monkeypatch.setattr(pipeline, "persist_last_frame_from_video", lambda *args, **kwargs: kwargs.get("preferred_url"))++ await pipeline.regen_shot_video(project.id, shot.id)++ call = generate_video.await_args+ assert call.args[0] == expected_first_frame and call.args[2] == 9+ assert call.kwargs["extra_image_urls"] == ["/static/previous-tail.png"]+ assert call.kwargs["generate_audio"] is True and call.kwargs["character_consistency"] is True+ assert call.kwargs["model"] == "seedance-2-5"+ assert call.kwargs["resolution"] == "720p" and call.kwargs["ratio"] == "9:16"+ assert shot.video_url == "/static/regenerated.mp4" and shot.last_frame_url == "/static/new-tail.png"+ assert project.final_video_url is Nonediff --git a/docs/API.md b/docs/API.mdindex 033e7c5..ee2b37d 100644--- a/docs/API.md+++ b/docs/API.md@@ -53,6 +53,21 @@ Authorization: Bearer <login-jwt>当前新建短片采用 `/api/projects` 分步创作流程:准备文案、创建或更新项目、生成分镜与素材,再由用户确认后合成成片。+`POST /api/projects` 与 `PATCH /api/projects/{project_id}` 使用 `pipeline_mode` 区分制作方式:++| 模式 | 素材与生成顺序 |+| --- | --- |+| `full` | 分镜脚本 → 参考图模式生成分镜图片 → 图片生成镜头视频 → 合成成片 |+| `image_text` | 分镜脚本 → 参考图模式生成分镜图片与配音 → 静图合成成片 |++当前新建页面默认选择 `full`,仍可选择 `image_text`。图片沿用选定模板的画风参考图、项目 `ref_image_url` 及已有镜头参考,锁定画风和角色;镜头视频以本镜图片作为首帧,并参考上一镜尾帧保持衔接。`image_model` / `video_model` 分别选择图片与视频模型,`image_resolution` / `video_resolution` 保存相应清晰度,`target_duration_sec` 为 15~180 秒的目标时长。完整视频模式沿用原有视频内置口播逻辑;静图模式保留外部配音。++画风图优先取模板 `seedream_config.style_ref_urls`,未配置时取模板封面;四个内置画风的旧模板行即使封面为空,也使用随代码提供的封面图。历史 `ref_images` 继续作为主体参考,用户图优先;后镜另加上一镜图片,画风参考独立传递。真实生成时,本地图片需同步发布到 OSS 或通过公网 `PUBLIC_BASE_URL/static/...` 访问,无法访问时返回明确错误,避免静默变成纯文字生图。镜头图片与视频参考均跳过需要鉴权的 TokenFree 产物地址,使用已保存的媒体。++调用 `POST /api/projects/{project_id}/generate` 每次只提交当前待执行的一段任务,阶段由后端素材就绪状态判定:`script`、`assets`、`videos`。素材阶段完成后,完整模式再次调用生成接口才进入视频阶段;静图模式跳过视频阶段。全部素材就绪时生成接口返回 409,改用 `POST /api/projects/{project_id}/compose` 合成。各阶段仅预扣本次尚未完成的媒体费用,已有图片和视频会复用。++单镜调整可使用 `POST /api/projects/{project_id}/shots/{shot_id}/regen-image` 与 `.../regen-video`;后者仅支持 `full`,并要求该镜已有图片。生成期间不能切换制作模式;通过 PATCH 切换模式会保留原分镜素材,作废原成片并按新模式回到待生成或待合成阶段。若要重新拆分镜,可调用生成接口并设置 `restart=true`,这会清除原分镜和素材。+旧版对话创作会话的创建、列表、详情、消息、取消、重试与 SSE 接口已删除,访问这些旧入口返回 404。其前端会话状态与轮询代码也已移除。仅保留 `POST /api/creation-sessions/{session_id}/open-editor`,归入“科普项目与作品”分组,用于将历史项目转入当前工作台。该接口会先等待旧任务停止并结算,再交接原项目及素材;历史任务执行与恢复代码、数据库记录保留。diff --git a/docs/BILLING.md b/docs/BILLING.mdindex 5f8f108..1dcd7ca 100644--- a/docs/BILLING.md+++ b/docs/BILLING.md@@ -88,6 +88,8 @@ billing_expr USD sell = official_CNY / 7.3 * 1.5## TaskRun 计费流程+AI 短视频的图片与镜头视频分阶段预占,只计尚未交付的素材。视频快照与执行共用分镜 `segment_script` 的段落时长、站点时长边界、声音开关、清晰度及画幅;不再只按旧 `shot.duration` 截整后预占。图片任务同时预留固定画风图、用户图与前镜引用槽位,视频任务预留本镜图片与前镜尾帧槽位,超过模型参考图上限时在受理阶段拒绝,不等付费调用后才发现参数不兼容。+任务中心分别展示「预估」「冻结状态」「实扣」「退款」与用量计费依据;未结算时实扣应显示未结算,而不是已消费 0 元。冻结是任务的预留金额,不是额外收费;总费用不能把冻结和实扣相加。取消/失败后按既有结算逻辑释放冻结,并保留真实已发生的上游用量。上游请求记录使用 `task_events` 的 `upstream.request.started/accepted/failed/poll` 事件,与 `billing_scope` 内的任务关联。记录真实 HTTP 方法、路径、模型、上游任务 ID、HTTP 响应码与耗时,以及脱敏后的请求/响应;内部任务参数不是实际 HTTP 请求体。轮询按状态变化采样,不按每轮重复刷事件。没有历史记录时显示「未记录」,不能事后伪造。请求日志不替代 `usage_events` 的真实计费依据,也不因日志写入失败重新提交上游。diff --git a/frontend/src/api.ts b/frontend/src/api.tsindex 36328f8..cfa8ade 100644--- a/frontend/src/api.ts+++ b/frontend/src/api.ts@@ -370,6 +370,10 @@ export const api = {style_prompt?: stringcharacter_prompt?: stringextra_prompt?: string+ image_model?: string+ video_model?: string+ image_resolution?: string+ video_resolution?: string}) {return request<Project>('/api/projects', { method: 'POST', body: JSON.stringify(body) })},diff --git a/frontend/src/components/layout/SiteNav.tsx b/frontend/src/components/layout/SiteNav.tsxindex b7046a3..3e4e0ec 100644--- a/frontend/src/components/layout/SiteNav.tsx+++ b/frontend/src/components/layout/SiteNav.tsx@@ -1,7 +1,7 @@import { Link, useLocation, useNavigate } from 'react-router-dom'import { useCallback, useEffect, useRef, useState } from 'react'import {- ChevronRight, CircleHelp, Clapperboard, CreditCard, House,+ ChevronRight, CircleHelp, Clapperboard, CodeXml, CreditCard, House,Menu, Plus, Store,Video, Workflow, X,} from 'lucide-react'@@ -11,6 +11,7 @@ import BrandMark from '../BrandMark'import CreateChoiceModal from '../ui/CreateChoiceModal'import { USER_UPDATED_EVENT } from '../../lib/userEvents'import { loadSessionUser } from '../../lib/sessionUser'+import { CODE_VIDEO_URL } from '../../lib/siteLinks'import { HOME_NAV, CREATION_NAV, RESOURCE_NAV, PERSONAL_NAV, resolveNavActive, type NavActive } from '../../lib/siteNavigation'import { useI18n } from '../../i18n'import LanguageSwitch from './LanguageSwitch'@@ -187,6 +188,13 @@ export default function SiteNav({ active }: Props) {</Link>}+ function renderCodeVideo(expanded = false) {+ return <a href={CODE_VIDEO_URL} target="_blank" rel="noopener noreferrer" className={`pf-topbar-link${expanded ? ' pf-topbar-menu-link' : ''}`} onClick={() => setMenuOpen(false)}>+ {expanded && <CodeXml size={18} strokeWidth={1.8} aria-hidden />}+ <span>{t('nav.codeVideo')}</span>+ </a>+ }+/** 市场入口遵从服务端能力开关,进入个人市场时清理团队请求范围。 */function renderMarketplace(expanded = false) {if (!marketplace?.enabled) return null@@ -204,6 +212,7 @@ export default function SiteNav({ active }: Props) {{renderLink(HOME_NAV)}{CREATION_NAV.map((item) => renderLink(item))}{renderMarketplace()}+ {renderCodeVideo()}{RESOURCE_NAV.map((item) => renderLink(item))}</nav><div className="pf-topbar-actions">@@ -221,7 +230,7 @@ export default function SiteNav({ active }: Props) {<nav aria-label={t('nav.main')}><div className="pf-topbar-menu-home">{renderLink(HOME_NAV, true)}</div><div className="pf-topbar-menu-group"><span>{t('nav.creation')}</span><div>{CREATION_NAV.map((item) => renderLink(item, true))}</div></div>- <div className="pf-topbar-menu-group"><div>{renderMarketplace(true)}{RESOURCE_NAV.map((item) => renderLink(item, true))}</div></div>+ <div className="pf-topbar-menu-group"><div>{renderMarketplace(true)}{renderCodeVideo(true)}{RESOURCE_NAV.map((item) => renderLink(item, true))}</div></div></nav><div className="pf-topbar-menu-footer"><LanguageSwitch />diff --git a/frontend/src/i18n/locales/en/shell.ts b/frontend/src/i18n/locales/en/shell.tsindex 62b1752..817febd 100644--- a/frontend/src/i18n/locales/en/shell.ts+++ b/frontend/src/i18n/locales/en/shell.ts@@ -67,6 +67,7 @@ export const enShell = {accountManagement: 'Account',balanceBilling: 'Balance & billing',assets: 'Assets',+ codeVideo: 'Code to Video',pricing: 'Pricing',help: 'Help',helpCenter: 'Help center',diff --git a/frontend/src/i18n/locales/zh/shell.ts b/frontend/src/i18n/locales/zh/shell.tsindex ee64b09..11d318e 100644--- a/frontend/src/i18n/locales/zh/shell.ts+++ b/frontend/src/i18n/locales/zh/shell.ts@@ -66,6 +66,7 @@ export const zhShell = {accountManagement: '账户管理',balanceBilling: '余额与账单',assets: '资产',+ codeVideo: '代码生视频',pricing: '定价',help: '帮助',helpCenter: '帮助中心',diff --git a/frontend/src/lib/shortVideoSettings.ts b/frontend/src/lib/shortVideoSettings.tsnew file mode 100644index 0000000..4cbe94d--- /dev/null+++ b/frontend/src/lib/shortVideoSettings.ts@@ -0,0 +1,66 @@+import type { MediaModelOption, MediaModelsCatalog, PipelineMode } from '../api'++type MediaSettings = {+ imageModel: string+ videoModel: string+ imageResolution: string+ videoResolution: string+ ratio: string+}++const RATIOS = ['9:16', '16:9', '1:1', '4:3', '21:9']++/** New projects use image-to-video; explicit still-image links keep their existing mode. */+export function shortVideoPipelineMode(value?: string | null): PipelineMode {+ return value === 'image_text' ? 'image_text' : 'full'+}++/** Reserve style/subject and continuity slots while accepting legacy catalogs without limits. */+function referenceModels(models: MediaModelOption[], imageReferences: number) {+ return models.filter(model => model.available !== false && (model.reference_limits === undefined || model.reference_limits.images >= imageReferences))+}++/** Only blank selections may use defaults; an unavailable explicit model must be replaced by the user. */+function selectModel(models: MediaModelOption[], current: string, preferred: string) {+ if (current) return models.find(model => model.id === current)+ return models.find(model => model.id === preferred)+ || models[0]+}++/** Priced resolutions take priority over the model's general capability list. */+function resolutions(model?: MediaModelOption) {+ return model?.available_resolutions ?? model?.allowed_resolutions ?? []+}++/** Keep supported quality choices and clamp incompatible choices after a model change. */+function selectResolution(model: MediaModelOption | undefined, current: string) {+ const allowed = resolutions(model)+ return allowed.includes(current) ? current+ : allowed.find(value => value === model?.defaults?.resolution) || allowed[0] || ''+}++/** Both stages use reference images; incompatible model parameters cannot start production. */+export function resolveShortVideoMediaSettings(catalog: MediaModelsCatalog | null, mode: PipelineMode, current: MediaSettings, imageReferenceCount = 2) {+ const imageOptions = referenceModels(catalog?.image_models ?? [], imageReferenceCount)+ const videoOptions = referenceModels(catalog?.video_models ?? [], 2)+ const image = selectModel(imageOptions, current.imageModel, catalog?.defaults.image_model || '')+ const video = selectModel(videoOptions, current.videoModel, catalog?.defaults.video_model || '')+ const imageRatios = image?.allowed_aspect_ratios ?? RATIOS+ const videoRatios = video?.allowed_aspect_ratios ?? RATIOS+ const ratios = RATIOS.filter(ratio => imageRatios.includes(ratio) && (mode === 'image_text' || videoRatios.includes(ratio)))+ const imageResolution = image ? selectResolution(image, current.imageResolution) : current.imageResolution+ const videoResolution = video ? selectResolution(video, current.videoResolution) : current.videoResolution+ const ratio = ratios.includes(current.ratio) ? current.ratio : ratios[0] || ''+ return {+ imageOptions, videoOptions, ratios,+ imageResolutions: resolutions(image), videoResolutions: resolutions(video),+ imageModel: current.imageModel || image?.id || '',+ videoModel: current.videoModel || video?.id || '',+ imageSelectionUnavailable: Boolean(catalog && current.imageModel && !image),+ videoSelectionUnavailable: Boolean(catalog && current.videoModel && !video),+ imageResolution: catalog ? imageResolution : current.imageResolution,+ videoResolution: catalog ? videoResolution : current.videoResolution,+ ratio: catalog ? ratio : current.ratio,+ ready: Boolean(catalog && image && imageResolution && ratio && (mode === 'image_text' || (video && videoResolution))),+ }+}diff --git a/frontend/src/lib/siteLinks.ts b/frontend/src/lib/siteLinks.tsindex 1d664d4..cf58a9f 100644--- a/frontend/src/lib/siteLinks.ts+++ b/frontend/src/lib/siteLinks.ts@@ -2,3 +2,4 @@export const GITHUB_REPO_URL = 'https://github.com/yi1108/printfilm'export const FILM_SKILLS_URL = 'https://www.gitcc.com/ai1/film-skills'+export const CODE_VIDEO_URL = 'https://fog.printfilm.com/'diff --git a/frontend/src/lib/status.ts b/frontend/src/lib/status.tsindex 3abc816..6a34c35 100644--- a/frontend/src/lib/status.ts+++ b/frontend/src/lib/status.ts@@ -213,7 +213,7 @@ export const KEPU_STEPS = [{ key: 'topic', label: '选题' },{ key: 'style', label: '风格' },{ key: 'confirm', label: '确认分镜' },- { key: 'assets', label: '画面与配音' },+ { key: 'assets', label: '参考图画面' },{ key: 'videos', label: '镜头视频' },{ key: 'compose', label: '合成预览' },]@@ -310,7 +310,7 @@ export function kepuPhaseHint(project: {}const phase = kepuBillingPhase(project)if (phase === 'script') return '先在风格页点「生成故事板」,本步只拆分镜脚本(预扣文字模型)。'- if (phase === 'assets') return '确认旁白与画面后开始生成:按镜头依次出图(后镜参考上一镜)+ 整片配音。'- if (phase === 'videos') return '画面与配音已齐。下一步按镜头依次出视频,后镜参考上一镜尾帧。'- return '素材已齐。拼接成片走后期合成(叠旁白字幕与配乐,扣费很少)。'+ if (phase === 'assets') return '确认分镜后,使用画风参考图逐镜生成图片,并参考前镜画面保持角色与风格一致。'+ if (phase === 'videos') return '图片已齐。使用每镜图片生成视频与声音,后镜参考上一镜尾帧延续画面。'+ return '镜头视频已齐。检查各镜头画面与声音后,即可合成成片。'}diff --git a/frontend/src/pages/HomePage.tsx b/frontend/src/pages/HomePage.tsxindex 7fb4093..462870c 100644--- a/frontend/src/pages/HomePage.tsx+++ b/frontend/src/pages/HomePage.tsx@@ -10,7 +10,7 @@ import { useI18n } from '../i18n'import { getDramaImageStylePreviewUrl } from '../lib/dramaImageStylePreviews'import { FILM_SKILLS_URL, GITHUB_REPO_URL } from '../lib/siteLinks'import { api, type Template } from '../api'-import { SHORT_VIDEO_LIST_PATH, shortVideoCreatePath } from '../lib/shortVideoRoutes'+import { SHORT_VIDEO_LIST_PATH } from '../lib/shortVideoRoutes'export default function HomePage() {const nav = useNavigate()@@ -18,14 +18,13 @@ export default function HomePage() {const loggedIn = Boolean(localStorage.getItem('token'))const [createOpen, setCreateOpen] = useState(false)const [templates, setTemplates] = useState<Template[]>([])- const [templatesError, setTemplatesError] = useState(false)useEffect(() => {let active = trueapi.templates().then((items) => {if (active) setTemplates(items)}).catch(() => {- if (active) setTemplatesError(true)+ if (active) setTemplates([])})return () => { active = false }}, [])@@ -146,31 +145,6 @@ export default function HomePage() {</button></section>- <section className="pf-land-caps" aria-labelledby="pf-land-templates-title">- <header className="pf-land-section-head">- <p className="pf-land-kicker">Styles</p>- <h2 id="pf-land-templates-title">{t('home.templatesTitle')}</h2>- <p className="pf-muted">{t('home.templatesHint')}</p>- </header>- <div className="pf-template-grid">- {templates.map((template) => (- <button- key={template.id}- type="button"- className="pf-template-card"- onClick={() => goAuthOr(shortVideoCreatePath(template.id))}- >- <img src={api.assetUrl(template.preview_cover)} alt="" loading="lazy" />- <div className="body">- <h3>{template.name}</h3>- <p>{template.description}</p>- </div>- </button>- ))}- </div>- {templatesError ? <p className="pf-muted">{t('home.templatesLoadFailed')}</p> : null}- </section>-<section className="pf-land-pipeline" aria-labelledby="pf-land-pipeline-title"><header className="pf-land-section-head"><p className="pf-land-kicker">{t('home.howKicker')}</p>diff --git a/frontend/src/pages/studio/CreateProjectPage.tsx b/frontend/src/pages/studio/CreateProjectPage.tsxindex 4125695..8f154a3 100644--- a/frontend/src/pages/studio/CreateProjectPage.tsx+++ b/frontend/src/pages/studio/CreateProjectPage.tsx@@ -1,14 +1,16 @@import { useEffect, useRef, useState, type FormEvent } from 'react'import { Link, useNavigate, useSearchParams } from 'react-router-dom'import { ArrowLeft, ArrowRight, Check, Clapperboard, Clock3, LoaderCircle, Save, Sparkles } from 'lucide-react'-import { api, type Project, type Template, type VoicePreset } from '../../api'+import { api, type PipelineMode, type Project, type Template, type VoicePreset } from '../../api'import AppShell from '../../components/layout/AppShell'import BillingErrorNotice from '../../components/billing/BillingErrorNotice'import Button from '../../components/ui/Button'import Stepper from '../../components/ui/Stepper'+import { MediaCostNotice } from '../../components/billing/MediaCostNotice'+import { useMediaModelsCatalog } from '../../hooks/useMediaModelsCatalog'import { creationTemplateId } from '../../lib/creationTemplates'-import { IMAGE_TEXT_STEPS } from '../../lib/imageTextStoryboard'-import { isRunning } from '../../lib/status'+import { resolveShortVideoMediaSettings, shortVideoPipelineMode } from '../../lib/shortVideoSettings'+import { isRunning, kepuSteps } from '../../lib/status'import { dialog } from '../../lib/dialog'import './shortVideoCreate.css'@@ -19,11 +21,19 @@ export default function CreateProjectPage() {const [params] = useSearchParams()const editId = Number(params.get('project')) || nullconst requestedTemplate = creationTemplateId(params.get('template'))+ const requestedPipelineMode = shortVideoPipelineMode(params.get('mode'))+ const returnPath = `/studio/new${params.size ? `?${params}` : ''}`const [templates, setTemplates] = useState<Template[]>([])const [voices, setVoices] = useState<VoicePreset[]>([])const [project, setProject] = useState<Project | null>(null)const [templateId, setTemplateId] = useState(requestedTemplate)const [ratio, setRatio] = useState('9:16')+ const [pipelineMode, setPipelineMode] = useState<PipelineMode>(requestedPipelineMode)+ const [imageModel, setImageModel] = useState('')+ const [videoModel, setVideoModel] = useState('')+ const [imageResolution, setImageResolution] = useState('')+ const [videoResolution, setVideoResolution] = useState('')+ const mediaCatalog = useMediaModelsCatalog()const [duration, setDuration] = useState(60)const [voice, setVoice] = useState('')const [mode, setMode] = useState<'idea' | 'copy'>('idea')@@ -46,13 +56,13 @@ export default function CreateProjectPage() {useEffect(() => {let disposed = falseif (!localStorage.getItem('token')) {- nav(`/auth?next=${encodeURIComponent('/studio/new' + (editId ? `?project=${editId}` : ''))}`, { replace: true })+ nav(`/auth?next=${encodeURIComponent(returnPath)}`, { replace: true })return}api.templates().then(rows => { if (!disposed) setTemplates(rows) }).catch(cause => { if (!disposed) setError(cause.message || '模板加载失败') })api.voices().then(rows => { if (!disposed) setVoices(rows) }).catch(() => { if (!disposed) setVoiceError(true) })return () => { disposed = true }- }, [nav, editId])+ }, [nav, editId, returnPath])useEffect(() => {let disposed = falseif (!editId) {@@ -61,6 +71,11 @@ export default function CreateProjectPage() {setLoading(false)setTemplateId(requestedTemplate)setRatio('9:16')+ setPipelineMode(requestedPipelineMode)+ setImageModel('')+ setVideoModel('')+ setImageResolution('')+ setVideoResolution('')setDuration(60)setVoice('')setMode('idea')@@ -83,6 +98,11 @@ export default function CreateProjectPage() {setProject(value)setTemplateId(creationTemplateId(value.template_id))setRatio(value.output_ratio || '9:16')+ setPipelineMode(shortVideoPipelineMode(value.pipeline_mode))+ setImageModel(value.image_model || '')+ setVideoModel(value.video_model || '')+ setImageResolution(value.image_resolution || '')+ setVideoResolution(value.video_resolution || '')setDuration(value.target_duration_sec || 60)setVoice(value.voice_id || '')setTitle(value.title)@@ -95,24 +115,30 @@ export default function CreateProjectPage() {}).catch(cause => { if (!disposed) setError(cause.message || '项目加载失败') }).finally(() => { if (!disposed) setLoading(false) })return () => { disposed = true }- }, [editId, requestedTemplate, nav])+ }, [editId, requestedTemplate, requestedPipelineMode, nav])const selectedTemplate = templates.find(item => item.id === templateId)+ const mediaSettings = resolveShortVideoMediaSettings(mediaCatalog, pipelineMode, { imageModel, videoModel, imageResolution, videoResolution, ratio }, project?.ref_image_url ? 3 : 2)const running = Boolean(project && (isRunning(project.status) || project.active_tasks?.some(task => ['pending', 'leased', 'running', 'awaiting_poll', 'awaiting_review', 'cancel_requested'].includes(task.status))))const disabled = Boolean(busy || loading || running)function payload(text: string, name: string) {return {template_id: templateId, title: name.trim().slice(0, 200) || text.trim().slice(0, 30),source_type: 'script' as const, source_text: text.trim(),- pipeline_mode: 'image_text' as const, resolution_mode: 'hd' as const,- output_ratio: ratio, target_duration_sec: duration, voice_id: voice,+ pipeline_mode: pipelineMode, resolution_mode: 'hd' as const,+ output_ratio: mediaSettings.ratio || ratio, target_duration_sec: duration, voice_id: voice,+ image_model: mediaSettings.imageModel, video_model: mediaSettings.videoModel,+ image_resolution: mediaSettings.imageResolution, video_resolution: mediaSettings.videoResolution,}}const draftFields = payload(copy, title)const draftChanged = Boolean(project && (project.title !== draftFields.title || project.source_text !== draftFields.source_text ||- project.template_id !== templateId || project.output_ratio !== ratio ||- (project.target_duration_sec || 60) !== duration || (project.voice_id || '') !== voice+ project.template_id !== templateId || project.output_ratio !== draftFields.output_ratio ||+ shortVideoPipelineMode(project.pipeline_mode) !== pipelineMode ||+ (project.target_duration_sec || 60) !== duration || (project.voice_id || '') !== voice ||+ (project.image_model || '') !== draftFields.image_model || (project.video_model || '') !== draftFields.video_model ||+ (project.image_resolution || '') !== draftFields.image_resolution || (project.video_resolution || '') !== draftFields.video_resolution))const canSaveDraft = !project?.shots.length && !project?.final_video_urlasync function createDraft(text: string, name: string) {@@ -173,11 +199,15 @@ export default function CreateProjectPage() {}async function generateStoryboard() {if (!copy.trim() || disabled || working.current || !selectedTemplate) return+ if (!mediaSettings.ready) {+ setError('当前模型不可用或参考图数量不足,请重新选择图片和视频模型、清晰度与画面比例。')+ return+ }working.current = truetry {const old = savedProject.currentif (old?.shots.length) {- const confirmed = await dialog.confirm({ title: '重新生成分镜', message: '新的文案与设置将重新生成分镜,并替换本项目已有的图片、配音和成片。', confirmText: '重新生成', tone: 'danger' })+ const confirmed = await dialog.confirm({ title: '重新生成分镜', message: '新的文案与设置将重新生成分镜,并替换本项目已有的图片、镜头视频、配音和成片。', confirmText: '重新生成', tone: 'danger' })if (!confirmed || !mounted.current) return}setBusy('正在保存并生成分镜…')@@ -200,7 +230,7 @@ export default function CreateProjectPage() {<div className="sv-create-page"><header className="sv-create-header"><div><Link className="sv-back" to="/history"><ArrowLeft size={16} /> 我的短片</Link><h1>{editId ? '编辑短片' : '创建短片'}</h1><p>从一个想法开始,每一步都可以查看和调整。</p></div>- <Stepper steps={IMAGE_TEXT_STEPS} current={step} />+ <Stepper steps={kepuSteps(pipelineMode)} current={pipelineMode === 'full' && step === 1 ? 2 : step} /></header>{error && <BillingErrorNotice message={error} />}{loading ? <div className="sv-loading"><LoaderCircle className="sv-spin" size={20} /> 正在加载项目…</div> : <>@@ -209,7 +239,7 @@ export default function CreateProjectPage() {<main>{step === 0 ? <form onSubmit={prepareCopy}><section className="sv-panel">- <div className="sv-section-heading"><span>01</span><div><h2>选择画面风格</h2><p>四种动画与插画风格,整个短片保持统一。</p></div></div>+ <div className="sv-section-heading"><span>01</span><div><h2>选择画面风格</h2><p>四种动画与插画风格,生图时使用画风参考图,逐镜延续角色与视觉风格。</p></div></div><div className="sv-style-grid" role="group" aria-label="画面风格">{templates.map(item => <button key={item.id} type="button" className={`sv-style-card${item.id === templateId ? ' is-selected' : ''}`} disabled={disabled} aria-pressed={item.id === templateId} onClick={() => setTemplateId(item.id)}><img src={api.assetUrl(item.preview_cover)} alt="" /><div><strong>{item.name}</strong><p>{item.description}</p></div>@@ -234,12 +264,22 @@ export default function CreateProjectPage() {</main><aside className="sv-panel sv-settings"><h2>短片设置</h2><p>先用默认设置,也可以按需要调整。</p>- <label className="sv-field"><span>画面比例</span><select value={ratio} onChange={event => setRatio(event.target.value)} disabled={disabled}><option value="9:16">9:16 竖屏</option><option value="16:9">16:9 横屏</option><option value="1:1">1:1 方形</option></select></label>+ <div className="sv-field"><span>成片方式</span><div className="sv-output-modes" role="group" aria-label="成片方式">{([{ id: 'full', label: 'AI 视频', desc: '参考图生图 → 图生视频 → 合成' }, { id: 'image_text', label: '静图成片', desc: '参考图生图 → 图片运镜与配音' }] as const).map(item => <button key={item.id} type="button" className={pipelineMode === item.id ? 'is-selected' : ''} aria-pressed={pipelineMode === item.id} disabled={disabled} onClick={() => setPipelineMode(item.id)}><strong>{item.label}</strong><span>{item.desc}</span>{pipelineMode === item.id && <Check size={14} />}</button>)}</div></div>+ <label className="sv-field"><span>画面比例</span><select value={mediaSettings.ratio} onChange={event => setRatio(event.target.value)} disabled={disabled || !mediaSettings.ratios.length}>{!mediaSettings.ratios.length && <option value="">暂无共同支持的画幅</option>}{mediaSettings.ratios.map(value => <option key={value} value={value}>{value}{value === '9:16' ? ' 竖屏' : value === '16:9' ? ' 横屏' : value === '1:1' ? ' 方形' : ''}</option>)}</select></label><label className="sv-field"><span>目标时长</span><select value={duration} onChange={event => setDuration(Number(event.target.value))} disabled={disabled}>{[...new Set([30, 60, 90, 120, 180, duration])].sort((a, b) => a - b).map(value => <option key={value} value={value}>约 {value} 秒</option>)}</select></label>- <label className="sv-field"><span>旁白音色</span><select value={voice} onChange={event => setVoice(event.target.value)} disabled={disabled}><option value="">默认普通话音色</option>{voice && !voices.some(item => (item.speaker || item.id) === voice) && <option value={voice}>项目原有音色</option>}{voices.map(item => <option key={item.id} value={item.speaker || item.id}>{item.label}</option>)}</select></label>- {voiceError && <p className="sv-saved-note">音色列表暂未加载,仍可使用默认配音。</p>}- <div className="sv-setting-summary"><Clapperboard size={17} /><div><strong>{selectedTemplate?.name || '3D 动画'}</strong><span>图片运镜 · 普通话旁白 · 中文字幕</span></div></div>- <div className="sv-workflow-hint"><Clock3 size={17} /><p>检查分镜后生成图片和配音,素材准备好后再合成视频。</p></div>+ {pipelineMode === 'image_text' ? <>+ <label className="sv-field"><span>旁白音色</span><select value={voice} onChange={event => setVoice(event.target.value)} disabled={disabled}><option value="">默认普通话音色</option>{voice && !voices.some(item => (item.speaker || item.id) === voice) && <option value={voice}>项目原有音色</option>}{voices.map(item => <option key={item.id} value={item.speaker || item.id}>{item.label}</option>)}</select></label>+ {voiceError && <p className="sv-saved-note">音色列表暂未加载,仍可使用默认配音。</p>}+ </> : <p className="sv-saved-note">视频模型生成旁白与声音。</p>}+ <details className="sv-model-settings" open={pipelineMode === 'full'}><summary>生成模型与清晰度</summary>+ <label className="sv-field"><span>参考图生图模型</span><select value={mediaSettings.imageModel} disabled={disabled || !mediaSettings.imageOptions.length} onChange={event => setImageModel(event.target.value)}>{mediaSettings.imageSelectionUnavailable && <option value={mediaSettings.imageModel} disabled>{mediaSettings.imageModel}(当前不可用)</option>}{!mediaSettings.imageOptions.length && !mediaSettings.imageSelectionUnavailable && <option value="">{mediaCatalog ? '暂无可用参考图模型' : '正在加载模型…'}</option>}{mediaSettings.imageOptions.map(item => <option key={item.id} value={item.id}>{item.label}</option>)}</select></label>+ <label className="sv-field"><span>图片清晰度</span><select value={mediaSettings.imageResolution} disabled={disabled || !mediaSettings.imageResolutions.length} onChange={event => setImageResolution(event.target.value)}>{!mediaSettings.imageResolutions.length && <option value={mediaSettings.imageResolution}>{mediaSettings.imageResolution || '请选择可用模型'}</option>}{mediaSettings.imageResolutions.map(value => <option key={value} value={value}>{value}</option>)}</select><MediaCostNotice modelId={mediaSettings.imageModel} resolution={mediaSettings.imageResolution} /></label>+ {pipelineMode === 'full' && <><label className="sv-field"><span>图生视频模型</span><select value={mediaSettings.videoModel} disabled={disabled || !mediaSettings.videoOptions.length} onChange={event => setVideoModel(event.target.value)}>{mediaSettings.videoSelectionUnavailable && <option value={mediaSettings.videoModel} disabled>{mediaSettings.videoModel}(当前不可用)</option>}{!mediaSettings.videoOptions.length && !mediaSettings.videoSelectionUnavailable && <option value="">{mediaCatalog ? '暂无可用图生视频模型' : '正在加载模型…'}</option>}{mediaSettings.videoOptions.map(item => <option key={item.id} value={item.id}>{item.label}</option>)}</select></label>+ <label className="sv-field"><span>视频清晰度</span><select value={mediaSettings.videoResolution} disabled={disabled || !mediaSettings.videoResolutions.length} onChange={event => setVideoResolution(event.target.value)}>{!mediaSettings.videoResolutions.length && <option value={mediaSettings.videoResolution}>{mediaSettings.videoResolution || '请选择可用模型'}</option>}{mediaSettings.videoResolutions.map(value => <option key={value} value={value}>{value}</option>)}</select><MediaCostNotice modelId={mediaSettings.videoModel} resolution={mediaSettings.videoResolution} seconds={1} /></label></>}+ {mediaCatalog && !mediaSettings.ready && <p className="sv-model-error" role="status">请重新选择可用模型,生图需支持 {project?.ref_image_url ? 3 : 2} 张参考图{pipelineMode === 'full' ? ',视频需支持 2 张参考图' : ''},并确认清晰度和画幅。</p>}+ </details>+ <div className="sv-setting-summary"><Clapperboard size={17} /><div><strong>{selectedTemplate?.name || '3D 动画'}</strong><span>{pipelineMode === 'full' ? '图生视频' : '图片运镜'} · 普通话旁白 · 中文字幕</span><span>使用画风参考图,并参考前镜画面保持一致。</span></div></div>+ <div className="sv-workflow-hint"><Clock3 size={17} /><p>{pipelineMode === 'full' ? '确认分镜后先生成参考图画面,再将图片逐镜生成为视频,检查镜头后合成成片。' : '检查分镜后生成图片和配音,素材准备好后再合成视频。'}</p></div></aside></div></>}diff --git a/frontend/src/pages/studio/StoryboardPage.tsx b/frontend/src/pages/studio/StoryboardPage.tsxindex 1a15fe9..696c041 100644--- a/frontend/src/pages/studio/StoryboardPage.tsx+++ b/frontend/src/pages/studio/StoryboardPage.tsx@@ -256,12 +256,12 @@ export default function StoryboardPage() {: shots.length === 0? '去风格页生成分镜': needsScriptConfirm- ? '确认分镜,逐镜出图与配音'+ ? '确认分镜,生成参考图画面': needsVideos- ? '逐镜出视频'+ ? '使用图片,逐镜生成视频': '继续生成'- // 工作台进度:完整模式要镜头视频 + 外部 TTS,静图模式只配音合成+ // 完整模式的默认旁白由视频模型生成;仅实际存在外部配音时展示 TTS 进度。const progressItems = useMemo(() => {if (!project) return []const list = project.shots || []@@ -275,13 +275,13 @@ export default function StoryboardPage() {{ label: '主题解析', done: true },{ label: '分镜脚本', done: list.length > 0 || !['DRAFT', 'SCRIPTING'].includes(project.status) },{- label: `画面生成 (${imgs}/${list.length || 0})`,+ label: `参考图画面 (${imgs}/${list.length || 0})`,done: list.length > 0 && imgs === list.length,},]if (full) {items.push({- label: `镜头视频 (${vids}/${list.length || 0})`,+ label: `镜头视频与声音 (${vids}/${list.length || 0})`,done:list.length > 0 &&(vids === list.length ||@@ -290,12 +290,14 @@ export default function StoryboardPage() {pct: stage === 'VIDEOING' ? project.progress : undefined,})}- items.push({- label: `配音合成 (${auds}/${list.length || 0})`,- done: list.length > 0 && auds === list.length,- run: stage === 'AUDIOING',- pct: stage === 'AUDIOING' ? project.progress : undefined,- })+ if (!full || auds > 0 || stage === 'AUDIOING') {+ items.push({+ label: `配音合成 (${auds}/${list.length || 0})`,+ done: list.length > 0 && auds === list.length,+ run: stage === 'AUDIOING',+ pct: stage === 'AUDIOING' ? project.progress : undefined,+ })+ }items.push({label: full ? '镜头拼接' : '成片渲染',done: Boolean(project.final_video_url) || project.status === 'DONE',@@ -964,7 +966,7 @@ title="用当前镜头重新拼接"<div className="pf-prompt-panel"><h4>内置提示词</h4><p className="pf-muted" style={{ fontSize: '0.72rem', margin: '0 0 0.45rem' }}>- 画风来自模板。角色是否出镜由 AI 按模板与主题决定;只有这里改过才覆盖本项目。+ 生图使用模板画风参考图,并参考前镜画面延续角色、服装与色彩;每镜图片再用于生成视频。</p>{([@@ -1246,6 +1248,11 @@ title="用当前镜头重新拼接"{shot.video_url ? '重生视频' : '出视频'}</button>) : null}+ {shot.video_url ? (+ <button type="button" className="op" onClick={() => setPreview({ kind: 'shot', shotNo: shot.shot_no, imageUrl: shot.image_url, videoUrl: shot.video_url, audioUrl: shot.audio_url, caption: shotCaption(shot) })}>+ 预览视频+ </button>+ ) : null}<buttontype="button"className="more"@@ -1283,8 +1290,8 @@ title="用当前镜头重新拼接")}<div className="pf-shot-footer"><span className="pf-muted" style={{ fontSize: '0.82rem' }}>- 总时长: {formatMmSs(totalDuration)} | 画面: {project.shots.length} 个 | 音频:{' '}- {project.shots.filter((s) => s.audio_url).length} 段 | 分辨率: 预览+ 总时长: {formatMmSs(totalDuration)} | 画面: {project.shots.filter((s) => s.image_url).length}/{project.shots.length} 个 | 视频:{' '}+ {project.shots.filter((s) => s.video_url).length}/{project.shots.length} 段 | 清晰度: {project.video_resolution || '默认'}</span><div className="pf-toolbar"><buttondiff --git a/frontend/src/pages/studio/shortVideoCreate.css b/frontend/src/pages/studio/shortVideoCreate.cssindex 90bc4a8..87f82c3 100644--- a/frontend/src/pages/studio/shortVideoCreate.css+++ b/frontend/src/pages/studio/shortVideoCreate.css@@ -35,6 +35,20 @@.sv-actions > span, .sv-saved-note { font-size: 12px; color: #929c87; line-height: 1.6; }.sv-settings { position: sticky; top: 20px; padding: 24px; }.sv-settings > p { margin-bottom: 24px; }+.sv-output-modes { display: grid; gap: 8px; }+.sv-output-modes button { position: relative; border: 1px solid #dfe5d9; border-radius: 10px; background: #fbfcf9; padding: 12px 30px 12px 12px; text-align: left; color: #293328; cursor: pointer; }+.sv-output-modes button.is-selected { border-color: #93bf36; background: #f8fcee; box-shadow: 0 0 0 2px #c9ed844a; }+.sv-output-modes strong, .sv-output-modes span { display: block; }+.sv-output-modes strong { font-size: 13px; }+.sv-output-modes span { color: #7a867c; font-size: 11px; margin-top: 5px; line-height: 1.6; }+.sv-output-modes svg { position: absolute; right: 12px; top: 13px; color: #607e22; }+.sv-model-settings { border-top: 1px solid #eaf0e0; margin-top: 22px; padding-top: 18px; }+.sv-model-settings summary { font-size: 13px; font-weight: 600; cursor: pointer; margin-bottom: 18px; }+.sv-model-settings .sv-field { margin-bottom: 16px; }+.sv-model-settings .media-cost-notice { font-size: 11px; font-weight: 400; line-height: 1.7; color: #7a867c; }+.sv-model-error { color: #a76232; font-size: 12px; line-height: 1.7; }+.sv-output-modes button:focus-visible, .sv-model-settings summary:focus-visible { outline: 2px solid #a6c95e; outline-offset: 3px; }+.sv-output-modes button:disabled { cursor: default; opacity: .6; }.sv-setting-summary, .sv-workflow-hint { border-top: 1px solid #eaf0e0; padding-top: 20px; display: flex; gap: 10px; color: #697956; margin-top: 24px; }.sv-setting-summary strong, .sv-setting-summary span { display: block; }.sv-setting-summary strong { font-size: 13px; }diff --git a/frontend/tests/short-video-settings.test.mjs b/frontend/tests/short-video-settings.test.mjsnew file mode 100644index 0000000..9231144--- /dev/null+++ b/frontend/tests/short-video-settings.test.mjs@@ -0,0 +1,93 @@+import assert from 'node:assert/strict'+import test from 'node:test'+import { resolveShortVideoMediaSettings, shortVideoPipelineMode } from '../src/lib/shortVideoSettings.ts'++const image = { id: 'image-ref', label: 'Reference images', available: true, reference_limits: { images: 4 }, allowed_aspect_ratios: ['9:16', '16:9', '1:1'], available_resolutions: ['2K', '4K'], defaults: { resolution: '2K' } }+const video = { id: 'video-ref', label: 'Image to video', available: true, reference_limits: { images: 2 }, allowed_aspect_ratios: ['16:9', '9:16'], available_resolutions: ['720p', '1080p'], defaults: { resolution: '720p' } }+const catalog = { image_models: [image], video_models: [video], defaults: { image_model: image.id, video_model: video.id } }+const settings = { imageModel: image.id, videoModel: video.id, imageResolution: '2K', videoResolution: '720p', ratio: '9:16' }++test('new short videos default to image-to-video while explicit still-image projects retain their mode', () => {+ assert.equal(shortVideoPipelineMode(null), 'full')+ assert.equal(shortVideoPipelineMode('full'), 'full')+ assert.equal(shortVideoPipelineMode('image_text'), 'image_text')+ assert.equal(shortVideoPipelineMode('unknown'), 'full')+})++test('video settings require reference-capable models and a shared supported aspect ratio', () => {+ const result = resolveShortVideoMediaSettings(catalog, 'full', settings)+ assert.equal(result.ready, true)+ assert.deepEqual(result.ratios, ['9:16', '16:9'])+ assert.equal(result.imageModel, image.id)+ assert.equal(result.videoModel, video.id)+ assert.equal(result.ratio, '9:16')+})++test('new projects choose compatible defaults instead of unavailable or text-only models', () => {+ const textOnly = { ...image, id: 'text-only', reference_limits: { images: 0 } }+ const unavailable = { ...video, id: 'offline', available: false }+ const result = resolveShortVideoMediaSettings({ ...catalog, image_models: [textOnly, image], video_models: [unavailable, video], defaults: { image_model: textOnly.id, video_model: unavailable.id } }, 'full', { ...settings, imageModel: '', videoModel: '' })+ assert.equal(result.imageModel, image.id)+ assert.equal(result.videoModel, video.id)+ assert.deepEqual(result.imageOptions.map(model => model.id), [image.id])+ assert.deepEqual(result.videoOptions.map(model => model.id), [video.id])+ assert.equal(result.ready, true)+})++test('explicit unavailable or removed models remain selected and block generation until replaced', () => {+ for (const imageModel of ['removed-image', 'offline-image', 'text-only']) {+ const result = resolveShortVideoMediaSettings({ ...catalog, image_models: [image, { ...image, id: 'offline-image', available: false }, { ...image, id: 'text-only', reference_limits: { images: 0 } }] }, 'full', { ...settings, imageModel, imageResolution: 'saved-quality' })+ assert.equal(result.imageModel, imageModel)+ assert.equal(result.imageResolution, 'saved-quality')+ assert.equal(result.imageSelectionUnavailable, true)+ assert.equal(result.ready, false)+ }+ const result = resolveShortVideoMediaSettings(catalog, 'full', { ...settings, videoModel: 'removed-video', videoResolution: 'saved-video-quality' })+ assert.equal(result.videoModel, 'removed-video')+ assert.equal(result.videoResolution, 'saved-video-quality')+ assert.equal(result.videoSelectionUnavailable, true)+ assert.equal(result.ready, false)+})++test('continuity requires two image slots per model and reserves a third image slot for an existing subject reference', () => {+ const capOne = { ...image, id: 'one-image-slot', reference_limits: { images: 1 } }+ const capTwo = { ...image, id: 'two-image-slots', reference_limits: { images: 2 } }+ const capOneVideo = { ...video, id: 'one-video-slot', reference_limits: { images: 1 } }+ const selection = { ...settings, imageModel: '', videoModel: '' }+ const result = resolveShortVideoMediaSettings({ ...catalog, image_models: [capOne, capTwo, image], video_models: [capOneVideo, video] }, 'full', selection)+ assert.deepEqual(result.imageOptions.map(model => model.id), [capTwo.id, image.id])+ assert.deepEqual(result.videoOptions.map(model => model.id), [video.id])+ const subject = resolveShortVideoMediaSettings({ ...catalog, image_models: [capTwo, image] }, 'full', selection, 3)+ assert.deepEqual(subject.imageOptions.map(model => model.id), [image.id])+ assert.equal(subject.ready, true)+ assert.equal(resolveShortVideoMediaSettings({ ...catalog, image_models: [capOne] }, 'image_text', selection).ready, false)+})++test('model changes replace unsupported resolution and aspect settings with supported defaults', () => {+ const result = resolveShortVideoMediaSettings(catalog, 'full', { ...settings, imageResolution: '8K', videoResolution: '480p', ratio: '1:1' })+ assert.equal(result.imageResolution, '2K')+ assert.equal(result.videoResolution, '720p')+ assert.equal(result.ratio, '9:16')+})++test('still-image projects do not need a video model and keep their wider set of image ratios', () => {+ const result = resolveShortVideoMediaSettings({ ...catalog, video_models: [] }, 'image_text', { ...settings, ratio: '1:1' })+ assert.equal(result.ready, true)+ assert.equal(result.ratio, '1:1')+ assert.equal(resolveShortVideoMediaSettings({ ...catalog, video_models: [] }, 'full', settings).ready, false)+})++test('missing catalogs preserve saved draft choices but cannot start media generation', () => {+ const result = resolveShortVideoMediaSettings(null, 'full', settings)+ assert.equal(result.ready, false)+ for (const [key, value] of Object.entries(settings)) assert.equal(result[key], value)+ assert.equal(resolveShortVideoMediaSettings({ ...catalog, image_models: [] }, 'full', settings).ready, false)+})++test('models with no shared ratio are blocked; legacy catalog reference limits remain compatible', () => {+ const incompatible = resolveShortVideoMediaSettings({ ...catalog, video_models: [{ ...video, allowed_aspect_ratios: ['21:9'] }] }, 'full', settings)+ assert.equal(incompatible.ready, false)+ assert.equal(incompatible.ratio, '')+ const legacy = resolveShortVideoMediaSettings({ ...catalog, image_models: [{ ...image, reference_limits: undefined }], video_models: [{ ...video, reference_limits: undefined }] }, 'full', settings)+ assert.equal(legacy.ready, true)+})