mulmocast 2.6.4 → 2.6.6

package/scripts/test/test_audio_mix.json

@@ -0,0 +1,91 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "title": "Audio Mix Manual Test (fixtures)",
+  "lang": "en",
+  "canvasSize": {
+    "width": 320,
+    "height": 180
+  },
+  "speechParams": {
+    "speakers": {
+      "Presenter": {
+        "provider": "openai",
+        "voiceId": "shimmer"
+      }
+    }
+  },
+  "audioParams": {
+    "bgmVolume": 0,
+    "movieVolume": 0.3
+  },
+  "beats": [
+    {
+      "speaker": "Presenter",
+      "text": "Low tone with narration.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_low.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "duration": 3.0,
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_low.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "Mid tone with narration.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_mid.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "duration": 3.0,
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_mid.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "High tone with narration.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_high.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "duration": 3.0,
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_high.mov"
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_audio_mix_beat_vol.json

@@ -0,0 +1,100 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "title": "Audio Mix Beat Volume Test (fixtures)",
+  "lang": "en",
+  "canvasSize": {
+    "width": 320,
+    "height": 180
+  },
+  "speechParams": {
+    "speakers": {
+      "Presenter": {
+        "provider": "openai",
+        "voiceId": "shimmer"
+      }
+    }
+  },
+  "audioParams": {
+    "bgmVolume": 0,
+    "movieVolume": 0.5
+  },
+  "beats": [
+    {
+      "speaker": "Presenter",
+      "text": "Low tone, beat movieVolume 0.1.",
+      "audioParams": {
+        "movieVolume": 0.1
+      },
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_low.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "Low tone, script default 0.5.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_low.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "Mid tone, beat movieVolume 1.0.",
+      "audioParams": {
+        "movieVolume": 1.0
+      },
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_mid.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "Mid tone, script default 0.5.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_mid.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "High tone, beat movieVolume 0.0, should be silent.",
+      "audioParams": {
+        "movieVolume": 0.0
+      },
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_high.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "High tone, script default 0.5.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_high.mov"
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_audio_mix_ducking.json

@@ -0,0 +1,91 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "title": "Audio Mix Ducking Test (fixtures)",
+  "lang": "en",
+  "canvasSize": {
+    "width": 320,
+    "height": 180
+  },
+  "speechParams": {
+    "speakers": {
+      "Presenter": {
+        "provider": "openai",
+        "voiceId": "shimmer"
+      }
+    }
+  },
+  "audioParams": {
+    "bgmVolume": 0,
+    "ducking": { "ratio": 0.3 }
+  },
+  "beats": [
+    {
+      "speaker": "Presenter",
+      "text": "Low tone with narration.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_low.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "duration": 3.0,
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_low.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "Mid tone with narration.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_mid.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "duration": 3.0,
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_mid.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "High tone with narration.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_high.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "duration": 3.0,
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_high.mov"
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_audio_mix_legacy.json

@@ -0,0 +1,90 @@
+{
+  "$mulmocast": {
+    "version": "1.1"
+  },
+  "title": "Audio Mix Legacy Test (fixtures)",
+  "lang": "en",
+  "canvasSize": {
+    "width": 320,
+    "height": 180
+  },
+  "speechParams": {
+    "speakers": {
+      "Presenter": {
+        "provider": "openai",
+        "voiceId": "shimmer"
+      }
+    }
+  },
+  "audioParams": {
+    "bgmVolume": 0
+  },
+  "beats": [
+    {
+      "speaker": "Presenter",
+      "text": "Low tone with narration.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_low.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "duration": 3.0,
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_low.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "Mid tone with narration.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_mid.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "duration": 3.0,
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_mid.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "text": "High tone with narration.",
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_high.mov"
+        }
+      }
+    },
+    {
+      "speaker": "Presenter",
+      "duration": 3.0,
+      "image": {
+        "type": "movie",
+        "source": {
+          "kind": "path",
+          "path": "fixtures/movie_tone_high.mov"
+        }
+      }
+    }
+  ]
+}

package/scripts/test/test_grok.json

@@ -0,0 +1,57 @@
+{
+  "$mulmocast": { "version": "1.1" },
+  "movieParams": {
+    "provider": "replicate",
+    "model": "xai/grok-imagine-video"
+  },
+  "audioParams": {
+    "bgmVolume": 0
+  },
+  "captionParams": {
+    "lang": "en"
+  },
+  "lang": "en",
+  "beats": [
+    {
+      "text": "Testing xai/grok-imagine-video — text-to-video, image-to-video, and duration varieties.",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "xai/grok-imagine-video test"
+        }
+      }
+    },
+    {
+      "id": "grok-t2v-5s",
+      "text": "Text-to-video, 5 seconds: a red fox trots through a snowy forest at dawn, pawprints left behind",
+      "duration": 5,
+      "moviePrompt": "a red fox trots through a snowy forest at dawn, pawprints left behind, soft golden light filtering through pine trees"
+    },
+    {
+      "id": "grok-t2v-8s",
+      "text": "Text-to-video, 8 seconds: timelapse of storm clouds forming over a mountain range",
+      "duration": 8,
+      "moviePrompt": "timelapse of dark storm clouds rolling in over a rugged mountain range, lightning flashes in the distance, dramatic cinematic lighting"
+    },
+    {
+      "id": "grok-t2v-10s",
+      "text": "Text-to-video, 10 seconds: bustling Tokyo crossing at night",
+      "duration": 10,
+      "moviePrompt": "aerial dolly shot over Shibuya crossing at night, neon lights reflecting on wet pavement, crowds of people crossing in all directions"
+    },
+    {
+      "id": "grok-i2v-5s",
+      "text": "Image-to-video, 5 seconds: ocean waves animated from a still image",
+      "duration": 5,
+      "imagePrompt": "a calm tropical beach at sunset, crystal-clear turquoise water, golden sand, photorealistic",
+      "moviePrompt": "gentle waves lapping the shore, palm trees swaying softly in the breeze, camera slowly pushing forward"
+    },
+    {
+      "id": "grok-i2v-8s",
+      "text": "Image-to-video, 8 seconds: city skyline coming to life",
+      "duration": 8,
+      "imagePrompt": "futuristic city skyline at dusk, glass skyscrapers with glowing windows, photorealistic",
+      "moviePrompt": "lights in the skyscraper windows flicker on one by one as night falls, slow upward pan along the tallest tower"
+    }
+  ]
+}

package/scripts/test/test_image_prompt_reference.json

@@ -0,0 +1,55 @@
+{
+  "$mulmocast": { "version": "1.1" },
+  "title": "Image Prompt Reference Tests",
+  "lang": "en",
+  "canvasSize": { "width": 1280, "height": 720 },
+  "imageParams": {
+    "images": {
+      "base_photo": {
+        "type": "image",
+        "source": { "kind": "url", "url": "https://images.unsplash.com/photo-1557682250-33bd709cbe85?w=1280&h=720&fit=crop" }
+      },
+      "from_prompt": {
+        "type": "imagePrompt",
+        "prompt": "A beautiful mountain landscape at sunset, photorealistic"
+      },
+      "stylized_by_name": {
+        "type": "imagePrompt",
+        "prompt": "Transform this image into a watercolor painting style",
+        "referenceImageName": "base_photo"
+      },
+      "stylized_by_source": {
+        "type": "imagePrompt",
+        "prompt": "Create an anime version of this gradient background",
+        "referenceImage": { "kind": "url", "url": "https://images.unsplash.com/photo-1557682250-33bd709cbe85?w=1280&h=720&fit=crop" }
+      },
+      "chained_ref": {
+        "type": "imagePrompt",
+        "prompt": "Add snow-capped peaks to this mountain scene",
+        "referenceImageName": "from_prompt"
+      }
+    }
+  },
+  "beats": [
+    {
+      "text": "Pattern 1: imagePrompt without reference (baseline)",
+      "imagePrompt": "A simple landscape",
+      "imageNames": ["from_prompt"]
+    },
+    {
+      "text": "Pattern 2: referenceImageName — reference another imageRefs key",
+      "imagePrompt": "A simple landscape",
+      "imageNames": ["stylized_by_name"]
+    },
+    {
+      "text": "Pattern 3: referenceImage — direct source",
+      "imagePrompt": "A simple landscape",
+      "imageNames": ["stylized_by_source"]
+    },
+    {
+      "text": "Pattern 4: chained reference — imagePrompt referencing another imagePrompt",
+      "imagePrompt": "A simple landscape",
+      "imageNames": ["chained_ref"]
+    }
+  ]
+}

package/scripts/test/test_image_references.json

@@ -0,0 +1,74 @@
+{
+  "$mulmocast": { "version": "1.1" },
+  "imageParams": {
+    "provider": "google",
+    "images": {
+      "character": {
+        "type": "imagePrompt",
+        "prompt": "a young woman with short black hair wearing a red leather jacket and dark sunglasses, standing on a neon-lit Tokyo street at night, photo realistic"
+      },
+      "black_cat": {
+        "type": "imagePrompt",
+        "prompt": "small black cat"
+      }
+    }
+  },
+  "movieParams": {
+    "provider": "google",
+    "model": "veo-3.1-generate-preview"
+  },
+  "lang": "en",
+  "beats": [
+    {
+      "id": "veo31_asset_and_style",
+      "text": "veo-3.1 with both ASSET and STYLE reference images",
+      "moviePrompt": "the woman runs through narrow alleyways, neon signs blurring in the rain",
+      "movieParams": {
+        "model": "veo-3.1-generate-preview",
+        "referenceImages": [
+          { "imageName": "character", "referenceType": "ASSET" },
+          { "imageName": "black_cat", "referenceType": "ASSET" }
+        ]
+      }
+    },
+    {
+      "id": "veo31_replicate_asset_reference",
+      "text": "google/veo-3.1 (replicate) with reference images",
+      "moviePrompt": "the woman walks through a crowded neon-lit Tokyo street at night, rain falling gently around her",
+      "movieParams": {
+        "provider": "replicate",
+        "model": "google/veo-3.1",
+        "referenceImages": [
+          { "imageName": "character", "referenceType": "ASSET" },
+          { "imageName": "black_cat", "referenceType": "ASSET" }
+        ]
+      }
+    },
+    {
+      "id": "kling_v3_omni_asset_reference",
+      "text": "kling-v3-omni-video with character ASSET reference image",
+      "moviePrompt": "the woman walks through a crowded neon-lit Tokyo street at night, rain falling gently around her",
+      "movieParams": {
+        "provider": "replicate",
+        "model": "kwaivgi/kling-v3-omni-video",
+        "referenceImages": [
+          { "imageName": "character", "referenceType": "ASSET" },
+          { "imageName": "black_cat", "referenceType": "ASSET" }
+        ]
+      }
+    },
+    {
+      "id": "grok_r2v_reference",
+      "text": "xai/grok-imagine-r2v with character and cat reference images",
+      "moviePrompt": "the woman walks through a crowded neon-lit Tokyo street at night, rain falling gently around her, the black cat weaving between her feet",
+      "movieParams": {
+        "provider": "replicate",
+        "model": "xai/grok-imagine-r2v",
+        "referenceImages": [
+          { "imageName": "character", "referenceType": "ASSET" },
+          { "imageName": "black_cat", "referenceType": "ASSET" }
+        ]
+      }
+    }
+  ]
+}

package/scripts/test/test_kling_v3.json

@@ -0,0 +1,54 @@
+{
+  "$mulmocast": { "version": "1.1" },
+  "movieParams": {
+    "provider": "replicate",
+    "model": "kwaivgi/kling-v3-video"
+  },
+  "imageParams": {
+    "provider": "google"
+  },
+  "audioParams": {
+    "bgmVolume": 0
+  },
+  "captionParams": {
+    "lang": "en"
+  },
+  "lang": "en",
+  "beats": [
+    {
+      "text": "Testing kwaivgi/kling-v3-video — text-to-video and image-to-video varieties.",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "kwaivgi/kling-v3-video test"
+        }
+      }
+    },
+    {
+      "id": "kling-v3-t2v-5s",
+      "text": "Text-to-video, 5 seconds: a red fox trots through a snowy forest at dawn, pawprints left behind",
+      "duration": 5,
+      "moviePrompt": "a red fox trots through a snowy forest at dawn, pawprints left behind, soft golden light filtering through pine trees"
+    },
+    {
+      "id": "kling-v3-t2v-10s",
+      "text": "Text-to-video, 10 seconds: bustling Tokyo crossing at night",
+      "duration": 10,
+      "moviePrompt": "aerial dolly shot over Shibuya crossing at night, neon lights reflecting on wet pavement, crowds of people crossing in all directions"
+    },
+    {
+      "id": "kling-v3-i2v-5s",
+      "text": "Image-to-video, 5 seconds: ocean waves animated from a still image",
+      "duration": 5,
+      "imagePrompt": "a calm tropical beach at sunset, crystal-clear turquoise water, golden sand, photorealistic",
+      "moviePrompt": "gentle waves lapping the shore, palm trees swaying softly in the breeze, camera slowly pushing forward"
+    },
+    {
+      "id": "kling-v3-i2v-10s",
+      "text": "Image-to-video, 10 seconds: city skyline coming to life",
+      "duration": 10,
+      "imagePrompt": "futuristic city skyline at dusk, glass skyscrapers with glowing windows, photorealistic",
+      "moviePrompt": "lights in the skyscraper windows flicker on one by one as night falls, slow upward pan along the tallest tower"
+    }
+  ]
+}

package/scripts/test/test_kling_v3_omni.json

@@ -0,0 +1,54 @@
+{
+  "$mulmocast": { "version": "1.1" },
+  "movieParams": {
+    "provider": "replicate",
+    "model": "kwaivgi/kling-v3-omni-video"
+  },
+  "imageParams": {
+    "provider": "google"
+  },
+  "audioParams": {
+    "bgmVolume": 0
+  },
+  "captionParams": {
+    "lang": "en"
+  },
+  "lang": "en",
+  "beats": [
+    {
+      "text": "Testing kwaivgi/kling-v3-omni-video — text-to-video and image-to-video varieties.",
+      "image": {
+        "type": "textSlide",
+        "slide": {
+          "title": "kwaivgi/kling-v3-omni-video test"
+        }
+      }
+    },
+    {
+      "id": "kling-omni-t2v-5s",
+      "text": "Text-to-video, 5 seconds: a red fox trots through a snowy forest at dawn, pawprints left behind",
+      "duration": 5,
+      "moviePrompt": "a red fox trots through a snowy forest at dawn, pawprints left behind, soft golden light filtering through pine trees"
+    },
+    {
+      "id": "kling-omni-t2v-10s",
+      "text": "Text-to-video, 10 seconds: bustling Tokyo crossing at night",
+      "duration": 10,
+      "moviePrompt": "aerial dolly shot over Shibuya crossing at night, neon lights reflecting on wet pavement, crowds of people crossing in all directions"
+    },
+    {
+      "id": "kling-omni-i2v-5s",
+      "text": "Image-to-video, 5 seconds: ocean waves animated from a still image",
+      "duration": 5,
+      "imagePrompt": "a calm tropical beach at sunset, crystal-clear turquoise water, golden sand, photorealistic",
+      "moviePrompt": "gentle waves lapping the shore, palm trees swaying softly in the breeze, camera slowly pushing forward"
+    },
+    {
+      "id": "kling-omni-i2v-10s",
+      "text": "Image-to-video, 10 seconds: city skyline coming to life",
+      "duration": 10,
+      "imagePrompt": "futuristic city skyline at dusk, glass skyscrapers with glowing windows, photorealistic",
+      "moviePrompt": "lights in the skyscraper windows flicker on one by one as night falls, slow upward pan along the tallest tower"
+    }
+  ]
+}