✨ feat: Added SlideIn and SlideOut video transition effects and optimized front-end implementation

app/models/schema.py

@@ -18,6 +18,15 @@ class VideoConcatMode(str, Enum):
     sequential = "sequential"
 
 
+class VideoTransitionMode(str, Enum):
+    none = None
+    shuffle = "Shuffle"
+    fade_in = "FadeIn"
+    fade_out = "FadeOut"
+    slide_in = "SlideIn"
+    slide_out = "SlideOut"
+
+
 class VideoAspect(str, Enum):
     landscape = "16:9"
     portrait = "9:16"
@@ -44,44 +53,6 @@ class MaterialInfo:
     duration: int = 0
 
 
-# VoiceNames = [
-#     # zh-CN
-#     "female-zh-CN-XiaoxiaoNeural",
-#     "female-zh-CN-XiaoyiNeural",
-#     "female-zh-CN-liaoning-XiaobeiNeural",
-#     "female-zh-CN-shaanxi-XiaoniNeural",
-#
-#     "male-zh-CN-YunjianNeural",
-#     "male-zh-CN-YunxiNeural",
-#     "male-zh-CN-YunxiaNeural",
-#     "male-zh-CN-YunyangNeural",
-#
-#     # "female-zh-HK-HiuGaaiNeural",
-#     # "female-zh-HK-HiuMaanNeural",
-#     # "male-zh-HK-WanLungNeural",
-#     #
-#     # "female-zh-TW-HsiaoChenNeural",
-#     # "female-zh-TW-HsiaoYuNeural",
-#     # "male-zh-TW-YunJheNeural",
-#
-#     # en-US
-#     "female-en-US-AnaNeural",
-#     "female-en-US-AriaNeural",
-#     "female-en-US-AvaNeural",
-#     "female-en-US-EmmaNeural",
-#     "female-en-US-JennyNeural",
-#     "female-en-US-MichelleNeural",
-#
-#     "male-en-US-AndrewNeural",
-#     "male-en-US-BrianNeural",
-#     "male-en-US-ChristopherNeural",
-#     "male-en-US-EricNeural",
-#     "male-en-US-GuyNeural",
-#     "male-en-US-RogerNeural",
-#     "male-en-US-SteffanNeural",
-# ]
-
-
 class VideoParams(BaseModel):
     """
     {
@@ -102,11 +73,14 @@ class VideoParams(BaseModel):
     video_terms: Optional[str | list] = None  # Keywords used to generate the video
     video_aspect: Optional[VideoAspect] = VideoAspect.portrait.value
     video_concat_mode: Optional[VideoConcatMode] = VideoConcatMode.random.value
+    video_transition_mode: Optional[VideoTransitionMode] = None
     video_clip_duration: Optional[int] = 5
     video_count: Optional[int] = 1
 
     video_source: Optional[str] = "pexels"
-    video_materials: Optional[List[MaterialInfo]] = None  # Materials used to generate the video
+    video_materials: Optional[List[MaterialInfo]] = (
+        None  # Materials used to generate the video
+    )
 
     video_language: Optional[str] = ""  # auto detect
 

app/services/task.py

@@ -164,6 +164,7 @@ def generate_final_videos(
     video_concat_mode = (
         params.video_concat_mode if params.video_count == 1 else VideoConcatMode.random
     )
+    video_transition_mode = params.video_transition_mode
 
     _progress = 50
     for i in range(params.video_count):
@@ -178,6 +179,7 @@ def generate_final_videos(
             audio_file=audio_file,
             video_aspect=params.video_aspect,
             video_concat_mode=video_concat_mode,
+            video_transition_mode=video_transition_mode,
             max_clip_duration=params.video_clip_duration,
             threads=params.n_threads,
         )

app/services/utils/video_effects.py

@@ -9,3 +9,13 @@ def fadein_transition(clip: Clip, t: float) -> Clip:
 # FadeOut
 def fadeout_transition(clip: Clip, t: float) -> Clip:
     return clip.with_effects([vfx.FadeOut(t)])
+
+
+# SlideIn
+def slidein_transition(clip: Clip, t: float, side: str) -> Clip:
+    return clip.with_effects([vfx.SlideIn(t, side)])
+
+
+# SlideOut
+def slideout_transition(clip: Clip, t: float, side: str) -> Clip:
+    return clip.with_effects([vfx.SlideOut(t, side)])

app/services/video.py

@@ -19,7 +19,14 @@ from moviepy.video.tools.subtitles import SubtitlesClip
 from PIL import ImageFont
 
 from app.models import const
-from app.models.schema import MaterialInfo, VideoAspect, VideoConcatMode, VideoParams
+from app.models.schema import (
+    MaterialInfo,
+    VideoAspect,
+    VideoConcatMode,
+    VideoParams,
+    VideoTransitionMode,
+)
+from app.services.utils import video_effects
 from app.utils import utils
 
 
@@ -45,6 +52,7 @@ def combine_videos(
     audio_file: str,
     video_aspect: VideoAspect = VideoAspect.portrait,
     video_concat_mode: VideoConcatMode = VideoConcatMode.random,
+    video_transition_mode: VideoTransitionMode = None,
     max_clip_duration: int = 5,
     threads: int = 2,
 ) -> str:
@@ -129,12 +137,34 @@ def combine_videos(
                     f"resizing video to {video_width} x {video_height}, clip size: {clip_w} x {clip_h}"
                 )
 
+            shuffle_side = random.choice(["left", "right", "top", "bottom"])
+            logger.info(f"Using transition mode: {video_transition_mode}")
+            if video_transition_mode.value == VideoTransitionMode.none.value:
+                clip = clip
+            elif video_transition_mode.value == VideoTransitionMode.fade_in.value:
+                clip = video_effects.fadein_transition(clip, 1)
+            elif video_transition_mode.value == VideoTransitionMode.fade_out.value:
+                clip = video_effects.fadeout_transition(clip, 1)
+            elif video_transition_mode.value == VideoTransitionMode.slide_in.value:
+                clip = video_effects.slidein_transition(clip, 1, shuffle_side)
+            elif video_transition_mode.value == VideoTransitionMode.slide_out.value:
+                clip = video_effects.slideout_transition(clip, 1, shuffle_side)
+            elif video_transition_mode.value == VideoTransitionMode.shuffle.value:
+                transition_funcs = [
+                    lambda c: video_effects.fadein_transition(c, 1),
+                    lambda c: video_effects.fadeout_transition(c, 1),
+                    lambda c: video_effects.slidein_transition(c, 1, shuffle_side),
+                    lambda c: video_effects.slideout_transition(c, 1, shuffle_side),
+                ]
+                shuffle_transition = random.choice(transition_funcs)
+                clip = shuffle_transition(clip)
+
             if clip.duration > max_clip_duration:
                 clip = clip.subclipped(0, max_clip_duration)
 
             clips.append(clip)
             video_duration += clip.duration
-
+    clips = [CompositeVideoClip([clip]) for clip in clips]
     video_clip = concatenate_videoclips(clips)
     video_clip = video_clip.with_fps(30)
     logger.info("writing")

webui/Main.py

@@ -8,7 +8,13 @@ from loguru import logger
 
 from app.config import config
 from app.models.const import FILE_TYPE_IMAGES, FILE_TYPE_VIDEOS
-from app.models.schema import MaterialInfo, VideoAspect, VideoConcatMode, VideoParams
+from app.models.schema import (
+    MaterialInfo,
+    VideoAspect,
+    VideoConcatMode,
+    VideoParams,
+    VideoTransitionMode,
+)
 from app.services import llm, voice
 from app.services import task as tm
 from app.utils import utils
@@ -544,6 +550,25 @@ with middle_panel:
             video_concat_modes[selected_index][1]
         )
 
+        # 视频转场模式
+        video_transition_modes = [
+            (tr("None"), VideoTransitionMode.none.value),
+            (tr("Shuffle"), VideoTransitionMode.shuffle.value),
+            (tr("FadeIn"), VideoTransitionMode.fade_in.value),
+            (tr("FadeOut"), VideoTransitionMode.fade_out.value),
+            (tr("SlideIn"), VideoTransitionMode.slide_in.value),
+            (tr("SlideOut"), VideoTransitionMode.slide_out.value),
+        ]
+        selected_index = st.selectbox(
+            tr("Video Transition Mode"),
+            options=range(len(video_transition_modes)),
+            format_func=lambda x: video_transition_modes[x][0],
+            index=0,
+        )
+        params.video_transition_mode = VideoTransitionMode(
+            video_transition_modes[selected_index][1]
+        )
+
         video_aspect_ratios = [
             (tr("Portrait"), VideoAspect.portrait.value),
             (tr("Landscape"), VideoAspect.landscape.value),

webui/i18n/de.json

@@ -16,6 +16,13 @@
     "Video Concat Mode": "Videoverkettungsmodus",
     "Random": "Zufällige Verkettung (empfohlen)",
     "Sequential": "Sequentielle Verkettung",
+    "Video Transition Mode": "Video Übergangsmodus",  
+    "None": "Kein Übergang",
+    "Shuffle": "Zufällige Übergänge",
+    "FadeIn": "FadeIn",
+    "FadeOut": "FadeOut",
+    "SlideIn": "SlideIn",
+    "SlideOut": "SlideOut",
     "Video Ratio": "Video-Seitenverhältnis",
     "Portrait": "Portrait 9:16",
     "Landscape": "Landschaft 16:9",

webui/i18n/en.json

@@ -16,6 +16,13 @@
     "Video Concat Mode": "Video Concatenation Mode",
     "Random": "Random Concatenation (Recommended)",
     "Sequential": "Sequential Concatenation",
+    "Video Transition Mode": "Video Transition Mode", 
+    "None": "None",
+    "Shuffle": "Shuffle",
+    "FadeIn": "FadeIn",
+    "FadeOut": "FadeOut",
+    "SlideIn": "SlideIn",
+    "SlideOut": "SlideOut",
     "Video Ratio": "Video Aspect Ratio",
     "Portrait": "Portrait 9:16",
     "Landscape": "Landscape 16:9",

webui/i18n/pt.json

@@ -16,6 +16,13 @@
     "Video Concat Mode": "Modo de Concatenação de Vídeo",
     "Random": "Concatenação Aleatória (Recomendado)",
     "Sequential": "Concatenação Sequencial",
+    "Video Transition Mode": "Modo de Transição de Vídeo",  
+    "None": "Nenhuma Transição",
+    "Shuffle": "Transição Aleatória",
+    "FadeIn": "FadeIn",
+    "FadeOut": "FadeOut",
+    "SlideIn": "SlideIn",
+    "SlideOut": "SlideOut",
     "Video Ratio": "Proporção do Vídeo",
     "Portrait": "Retrato 9:16",
     "Landscape": "Paisagem 16:9",

webui/i18n/vi.json

@@ -16,6 +16,13 @@
     "Video Concat Mode": "Chế Độ Nối Video",
     "Random": "Nối Ngẫu Nhiên (Được Khuyến Nghị)",
     "Sequential": "Nối Theo Thứ Tự",
+    "Video Transition Mode": "Chế Độ Chuyển Đổi Video",
+    "None": "Không Có Chuyển Đổi",  
+    "Shuffle": "Chuyển Đổi Ngẫu Nhiên",
+    "FadeIn": "FadeIn",
+    "FadeOut": "FadeOut",
+    "SlideIn": "SlideIn",
+    "SlideOut": "SlideOut",
     "Video Ratio": "Tỷ Lệ Khung Hình Video",
     "Portrait": "Dọc 9:16",
     "Landscape": "Ngang 16:9",

webui/i18n/zh.json

@@ -16,6 +16,13 @@
     "Video Concat Mode": "视频拼接模式",
     "Random": "随机拼接（推荐）",
     "Sequential": "顺序拼接",
+    "Video Transition Mode": "视频转场模式",
+    "None": "无转场",
+    "Shuffle": "随机转场",
+    "FadeIn": "渐入",
+    "FadeOut": "渐出",
+    "SlideIn": "滑动入",
+    "SlideOut": "滑动出",
     "Video Ratio": "视频比例",
     "Portrait": "竖屏 9:16（抖音视频）",
     "Landscape": "横屏 16:9（西瓜视频）",