problem with off-screen voiceover【画外音问题】
After repeated attempts, the model consistently assumes that the voice-over is spoken by the character's mouth and drives the character's lip movements accordingly. Could you please help me check what might be wrong with the prompt? 【反复尝试后，模型始终会认为画外音是角色嘴里说出来的，并驱动角色嘴部说话。请帮我看看，提示词有哪里不对。】
subject_definitions:
<Subject 1> (S1) is the person in <Picture 2> and <Picture 1> - fully preserved for appearance, hairstyle, clothing, and posture.
<Picture 1> is a fully preserved scene reference for the desk area - it provides the desk surface, blue ceramic mug, pen holder, desk lamp, and the map on the desktop, within a windowless, enclosed indoor environment. Behind the character is a sealed wall with a wooden door - no windows are present anywhere in this room.
summary:
[reference generation] A 14-second single shot inside a windowless, enclosed bedroom. <Subject 1> sits at the desk, picks up a pen from the map and marks it, while keeping his mouth completely closed throughout. The camera is positioned on the desk surface, shooting upward at a low angle. Behind the character is a sealed concrete wall with a wooden door - no windows exist in this room.
retention_analysis:
<Subject 1> (appears in [Shot 1]): fully_preserved - the character's appearance, clothing, and posture are exactly as in <Picture 2>.
<Picture 1> (desk area): fully_preserved - the desk surface, blue ceramic mug, pen holder, desk lamp, and map on the desktop are fully retained, within a windowless, enclosed indoor setting.
detailed_description:
The target video adopts a photorealistic, minimalist interior style with neutral lighting from overhead fluorescent tubes, set within a windowless, enclosed bedroom environment as defined by <Picture 1>. Behind the character's back is a sealed concrete wall with a wooden door - there are no windows anywhere in the room, and no natural light enters from outside.
[Shot 1] The shot opens with the camera positioned on the desk surface, shooting upward at a low angle toward <Subject 1>. The character dominates the frame, with the blue ceramic mug occupying the lower-right foreground (softly out of focus), its steam visibly rising. On the left side of the frame, the desk lamp is visible, turned on and casting a warm glow. In the background behind the character, a sealed concrete wall and a wooden door are visible - no windows, no exterior light. The camera performs a static shot. The man (S2) says in an off-screen voiceover: [Chinese] 和平铁路的轨道是超级金属做的——应该还可以用。从这里到喜马拉雅山，走和平铁路要六千七百公里，走公路只需要三千八百公里。 while his lips remain completely closed. <Subject 1> reaches his hand toward the map spread on the desk, picks up a pen from its surface, and begins to mark locations on the map while thinking. The pen produces a soft scratching sound against the paper as he draws lines and circles.
overall_soundscape:
Low-level room tone and the continuous hum of the fluorescent lights persist throughout the shot, within the confined, windowless space.
non_diegetic_music:
N/A
I had no trouble with adding a narrator voice-over and have it not affect lip movements of the subject(s) in the video.
I simply used the following form in my prompt:
Female narrator voice, saying: "Here we see..."
I don't think you should refer to the narrator as 'the man' or it will assume you mean 'the man' seen on screen at the time, and thus animate the lips.
朋友，你解决了吗？？我也遇到 ，这个内心独白，时灵时不灵的，一会儿可以 一会儿不可以 ，好烦
朋友，你解决了吗？？我也遇到 ，这个内心独白，时灵时不灵的，一会儿可以 一会儿不可以 ，好烦
有朋友提出建议，说是将【while his lips remain completely closed】改为【while <Subject 1>'s lips remain completely closed】会好一些。我试了试，有一些效果，但不能完全奏效。
我尝试了下面所有的写法，无一奏效：
1、、、、、、、、、、、、、、、
subject_definitions:
<Picture 1> is the tent interior reference image, showing a man sitting inside the tent with a cup in his hand, drinking water.
<Subject 1> is the man in <Picture 1>, wearing dark green clothing and gloves.
<Subject 2> is the cup in <Picture 1>.
<Subject 3> is the backpack in <Picture 1>.
<Audio 1> is the voice timbre reference for <Subject 1>.
summary:
[keyframe completion + audio reference] The target video is a 5-second static shot, with <Picture 1> serving as the first frame. <Subject 1> puts the lid on <Subject 2>, places it into <Subject 3>, and zips it closed. The entire video is accompanied by <Subject 1>'s inner monologue.
retention_analysis:
<Picture 1> (first frame of [Shot 1]): fully_preserved — the video uses <Picture 1> as the fixed background, with the tent interior environment, character posture, and item layout fully retained.
<Subject 1> (appears in [Shot 1]): fully_preserved — <Subject 1>'s appearance is derived from <Picture 1>, fully retained.
<Subject 2> (appears in [Shot 1]): fully_preserved — <Subject 2>'s appearance is derived from <Picture 1>, fully retained.
<Subject 3> (appears in [Shot 1]): fully_preserved — <Subject 3>'s appearance is derived from <Picture 1>, fully retained.
<Audio 1> (voice timbre reference for <Subject 1>): reference — <Subject 1>'s inner monologue references the vocal timbre and delivery characteristics of <Audio 1>, without copying the original signal.
detailed_description:
The target video adopts a cinematic photorealistic style, with an overall dim palette, illuminated by a warm light inside the tent, providing limited but warm lighting.
[Shot 1] The shot opens with <Picture 1> as the fixed background, with <Subject 1> sitting inside the tent, holding <Subject 2> and drinking water. <Subject 1> then puts the lid on <Subject 2>, places the cup into <Subject 3> beside him, and zips <Subject 3> closed. During the process of putting the cup into the backpack and zipping it, <Subject 1> (S1) says in an off-screen voiceover with the vocal timbre referenced from <Audio 1>: [Chinese] 不早了，赶快休息吧。 while <Subject 1>'s lips remain completely closed.
overall_soundscape:
The lid of <Subject 2> produces a soft plastic or metal click as it is closed. The cup rubbing against fabric as it is placed into <Subject 3>, and the continuous clicking of zipper teeth as the backpack is zipped closed. Faint wind sounds can be heard from outside the tent. These ambient sounds continue throughout the video.
non_diegetic_music:
N/A
2、、、、、、、、、、、、、、、、、、、、、、、、
subject_definitions:
<Picture 1> is the tent interior reference image, showing a man sitting inside the tent with a cup in his hand, drinking water.
<Subject 1> is the man in <Picture 1>, wearing dark green clothing and gloves.
<Subject 2> is the cup in <Picture 1>.
<Subject 3> is the backpack in <Picture 1>.
summary:
[keyframe completion + audio reference] The target video is a 5-second static shot, with <Picture 1> serving as the first frame. <Subject 1> puts the lid on <Subject 2>, places it into <Subject 3>, and zips it closed. The entire video is accompanied by <Subject 1>'s inner monologue.
retention_analysis:
<Picture 1> (first frame of [Shot 1]): fully_preserved — the video uses <Picture 1> as the fixed background, with the tent interior environment, character posture, and item layout fully retained.
<Subject 1> (appears in [Shot 1]): fully_preserved — <Subject 1>'s appearance is derived from <Picture 1>, fully retained.
<Subject 2> (appears in [Shot 1]): fully_preserved — <Subject 2>'s appearance is derived from <Picture 1>, fully retained.
<Subject 3> (appears in [Shot 1]): fully_preserved — <Subject 3>'s appearance is derived from <Picture 1>, fully retained.
detailed_description:
The target video adopts a cinematic photorealistic style, with an overall dim palette, illuminated by a warm light inside the tent, providing limited but warm lighting.
[Shot 1] The shot opens with <Picture 1> as the fixed background, with <Subject 1> sitting inside the tent, holding <Subject 2> and drinking water. <Subject 1> then puts the lid on <Subject 2>, places the cup into <Subject 3> beside him, and zips <Subject 3> closed. During the process of putting the cup into the backpack and zipping it, male says in an off-screen voiceover with the vocal timbre referenced from <Audio 1>: [Chinese] 不早了，赶快休息吧。 while <Subject 1>'s lips remain completely closed.
overall_soundscape:
The lid of <Subject 2> produces a soft plastic or metal click as it is closed. The cup rubbing against fabric as it is placed into <Subject 3>, and the continuous clicking of zipper teeth as the backpack is zipped closed. Faint wind sounds can be heard from outside the tent. These ambient sounds continue throughout the video.
non_diegetic_music:
N/A
3、、、、、、、、、、、、、、、、、、、、、、、、、
subject_definitions:
<Picture 1> is the tent interior reference image, showing a man sitting inside the tent with a cup in his hand, drinking water.
<Subject 1> is the man in <Picture 1>, wearing dark green clothing and gloves.
<Subject 2> is the cup in <Picture 1>.
<Subject 3> is the backpack in <Picture 1>.
summary:
[keyframe completion + audio reference] The target video is a 5-second static shot, with <Picture 1> serving as the first frame. <Subject 1> puts the lid on <Subject 2>, places it into <Subject 3>, and zips it closed. The entire video is accompanied by <Subject 1>'s inner monologue.
retention_analysis:
<Picture 1> (first frame of [Shot 1]): fully_preserved — the video uses <Picture 1> as the fixed background, with the tent interior environment, character posture, and item layout fully retained.
<Subject 1> (appears in [Shot 1]): fully_preserved — <Subject 1>'s appearance is derived from <Picture 1>, fully retained.
<Subject 2> (appears in [Shot 1]): fully_preserved — <Subject 2>'s appearance is derived from <Picture 1>, fully retained.
<Subject 3> (appears in [Shot 1]): fully_preserved — <Subject 3>'s appearance is derived from <Picture 1>, fully retained.
detailed_description:
The target video adopts a cinematic photorealistic style, with an overall dim palette, illuminated by a warm light inside the tent, providing limited but warm lighting.
[Shot 1] The shot opens with <Picture 1> as the fixed background, with <Subject 1> sitting inside the tent, holding <Subject 2> and drinking water. <Subject 1> then puts the lid on <Subject 2>, places the cup into <Subject 3> beside him, and zips <Subject 3> closed. During the process of putting the cup into the backpack and zipping it, male narrator voice saying with the vocal timbre referenced from <Audio 1>: [Chinese] 不早了，赶快休息吧。 while <Subject 1>'s lips remain completely closed.
overall_soundscape:
The lid of <Subject 2> produces a soft plastic or metal click as it is closed. The cup rubbing against fabric as it is placed into <Subject 3>, and the continuous clicking of zipper teeth as the backpack is zipped closed. Faint wind sounds can be heard from outside the tent. These ambient sounds continue throughout the video.
non_diegetic_music:
N/A
4、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、
subject_definitions:
<Picture 1> is the tent interior reference image, showing a man sitting inside the tent with a cup in his hand, drinking water.
<Subject 1> is the man in <Picture 1>, wearing dark green clothing and gloves.
<Subject 2> is the cup in <Picture 1>.
<Subject 3> is the backpack in <Picture 1>.
summary:
[keyframe completion + audio reference] The target video is a 5-second static shot, with <Picture 1> serving as the first frame. <Subject 1> puts the lid on <Subject 2>, places it into <Subject 3>, and zips it closed. The entire video is accompanied by <Subject 1>'s inner monologue.
retention_analysis:
<Picture 1> (first frame of [Shot 1]): fully_preserved — the video uses <Picture 1> as the fixed background, with the tent interior environment, character posture, and item layout fully retained.
<Subject 1> (appears in [Shot 1]): fully_preserved — <Subject 1>'s appearance is derived from <Picture 1>, fully retained.
<Subject 2> (appears in [Shot 1]): fully_preserved — <Subject 2>'s appearance is derived from <Picture 1>, fully retained.
<Subject 3> (appears in [Shot 1]): fully_preserved — <Subject 3>'s appearance is derived from <Picture 1>, fully retained.
detailed_description:
The target video adopts a cinematic photorealistic style, with an overall dim palette, illuminated by a warm light inside the tent, providing limited but warm lighting.
[Shot 1] The shot opens with <Picture 1> as the fixed background, with <Subject 1> sitting inside the tent, holding <Subject 2> and drinking water. <Subject 1> then puts the lid on <Subject 2>, places the cup into <Subject 3> beside him, and zips <Subject 3> closed. Male narrator voice saying with the vocal timbre referenced from <Audio 1>: [Chinese] 不早了，赶快休息吧。 while <Subject 1>'s lips remain completely closed.
overall_soundscape:
The lid of <Subject 2> produces a soft plastic or metal click as it is closed. The cup rubbing against fabric as it is placed into <Subject 3>, and the continuous clicking of zipper teeth as the backpack is zipped closed. Faint wind sounds can be heard from outside the tent. These ambient sounds continue throughout the video.
non_diegetic_music:
N/A
5、、、、、、、、、、、、、、、、、、、、、
subject_definitions:
<Picture 1> is the tent interior reference image, showing a man sitting inside the tent with a cup in his hand, drinking water.
<Subject 1> is the man in <Picture 1>, wearing dark green clothing and gloves.
<Subject 2> is the cup in <Picture 1>.
<Subject 3> is the backpack in <Picture 1>.
summary:
[keyframe completion + audio reference] The target video is a 5-second static shot, with <Picture 1> serving as the first frame. <Subject 1> puts the lid on <Subject 2>, places it into <Subject 3>, and zips it closed. The entire video is accompanied by <Subject 1>'s inner monologue.
retention_analysis:
<Picture 1> (first frame of [Shot 1]): fully_preserved — the video uses <Picture 1> as the fixed background, with the tent interior environment, character posture, and item layout fully retained.
<Subject 1> (appears in [Shot 1]): fully_preserved — <Subject 1>'s appearance is derived from <Picture 1>, fully retained.
<Subject 2> (appears in [Shot 1]): fully_preserved — <Subject 2>'s appearance is derived from <Picture 1>, fully retained.
<Subject 3> (appears in [Shot 1]): fully_preserved — <Subject 3>'s appearance is derived from <Picture 1>, fully retained.
detailed_description:
The target video adopts a cinematic photorealistic style, with an overall dim palette, illuminated by a warm light inside the tent, providing limited but warm lighting.
[Shot 1] The shot opens with <Picture 1> as the fixed background, with <Subject 1> sitting inside the tent, holding <Subject 2> and drinking water. <Subject 1> then puts the lid on <Subject 2>, places the cup into <Subject 3> beside him, and zips <Subject 3> closed. Male narrator voice saying with the vocal timbre referenced from <Audio 1>: [Chinese] 不早了，赶快休息吧。 while <Subject 1>'s lips remain completely closed.
overall_soundscape:
The lid of <Subject 2> produces a soft plastic or metal click as it is closed. The cup rubbing against fabric as it is placed into <Subject 3>, and the continuous clicking of zipper teeth as the backpack is zipped closed. Faint wind sounds can be heard from outside the tent. These ambient sounds continue throughout the video.
non_diegetic_music:
N/A
6、、、、、、、、、、、、、、、、、、、、、
subject_definitions:
<Picture 1> is the tent interior reference image, showing a man sitting inside the tent with a cup in his hand, drinking water.
<Subject 1> is the man in <Picture 1>, wearing dark green clothing and gloves.
<Subject 2> is the cup in <Picture 1>.
<Subject 3> is the backpack in <Picture 1>.
summary:
[keyframe completion + audio reference] The target video is a 5-second static shot, with <Picture 1> serving as the first frame. <Subject 1> puts the lid on <Subject 2>, places it into <Subject 3>, and zips it closed. The entire video is accompanied by <Subject 1>'s inner monologue.
retention_analysis:
<Picture 1> (first frame of [Shot 1]): fully_preserved — the video uses <Picture 1> as the fixed background, with the tent interior environment, character posture, and item layout fully retained.
<Subject 1> (appears in [Shot 1]): fully_preserved — <Subject 1>'s appearance is derived from <Picture 1>, fully retained.
<Subject 2> (appears in [Shot 1]): fully_preserved — <Subject 2>'s appearance is derived from <Picture 1>, fully retained.
<Subject 3> (appears in [Shot 1]): fully_preserved — <Subject 3>'s appearance is derived from <Picture 1>, fully retained.
detailed_description:
The target video adopts a cinematic photorealistic style, with an overall dim palette, illuminated by a warm light inside the tent, providing limited but warm lighting.
[Shot 1] The shot opens with <Picture 1> as the fixed background, with <Subject 1> sitting inside the tent, holding <Subject 2> and drinking water. <Subject 1> then puts the lid on <Subject 2>, places the cup into <Subject 3> beside him, and zips <Subject 3> closed. Male narrator voice saying with the vocal timbre referenced from <Audio 1>: "不早了，赶快休息吧。" while <Subject 1>'s lips remain completely closed.
overall_soundscape:
The lid of <Subject 2> produces a soft plastic or metal click as it is closed. The cup rubbing against fabric as it is placed into <Subject 3>, and the continuous clicking of zipper teeth as the backpack is zipped closed. Faint wind sounds can be heard from outside the tent. These ambient sounds continue throughout the video.
non_diegetic_music:
N/A
7、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、、
subject_definitions:
<Picture 1> is the tent interior reference image, showing a man sitting inside the tent with a cup in his hand, drinking water.
<Subject 1> is the man in <Picture 1>, wearing dark green clothing and gloves.
<Subject 2> is the cup in <Picture 1>.
<Subject 3> is the backpack in <Picture 1>.
<Subject 4> (S1) is an off-screen voiceover.
<Audio 1> is the voice timbre reference for <Subject 4>.
summary:
[keyframe completion + audio reference] The target video is a 5-second static shot, with <Picture 1> serving as the first frame. <Subject 1> puts the lid on <Subject 2>, places it into <Subject 3>, and zips it closed. The entire video is accompanied by <Subject 1>'s inner monologue.
retention_analysis:
<Picture 1> (first frame of [Shot 1]): fully_preserved — the video uses <Picture 1> as the fixed background, with the tent interior environment, character posture, and item layout fully retained.
<Subject 1> (appears in [Shot 1]): fully_preserved — <Subject 1>'s appearance is derived from <Picture 1>, fully retained.
<Subject 2> (appears in [Shot 1]): fully_preserved — <Subject 2>'s appearance is derived from <Picture 1>, fully retained.
<Subject 3> (appears in [Shot 1]): fully_preserved — <Subject 3>'s appearance is derived from <Picture 1>, fully retained.
<Audio 1> (voice timbre reference for <Subject 4>): reference — <Subject 4>'s inner monologue references the vocal timbre and delivery characteristics of <Audio 1>, without copying the original signal.
detailed_description:
The target video adopts a cinematic photorealistic style, with an overall dim palette, illuminated by a warm light inside the tent, providing limited but warm lighting.
[Shot 1] The shot opens with <Picture 1> as the fixed background, with <Subject 1> sitting inside the tent, holding <Subject 2> and drinking water. After <Subject 1> finishing his water, <Subject 4> (S1) says in an off-screen voiceover: [Chinese] 不早了，赶快休息吧。 while <Subject 1>'s lips remain completely closed. In the mean time <Subject 1> puts the lid on <Subject 2>, places the cup into <Subject 3> beside him, and zips <Subject 3> closed.
overall_soundscape:
The lid of <Subject 2> produces a soft plastic or metal click as it is closed. The cup rubbing against fabric as it is placed into <Subject 3>, and the continuous clicking of zipper teeth as the backpack is zipped closed. Faint wind sounds can be heard from outside the tent. These ambient sounds continue throughout the video.
non_diegetic_music:
N/A
8、、、、、、、、、、、、、、、、、、、、、、
subject_definitions:
<Picture 1> is the tent interior reference image, showing a man sitting inside the tent with a cup in his hand, drinking water.
<Subject 1> (S1) is the man in <Picture 1>, wearing dark green clothing and gloves.
<Subject 2> is the cup in <Picture 1>.
<Subject 3> is the backpack in <Picture 1>.
<Audio 1> is the voice timbre reference for <Subject 1> (S1).
summary:
[keyframe completion + audio reference] The target video is a 5-second static shot, with <Picture 1> serving as the first frame. <Subject 1> puts the lid on <Subject 2>, places it into <Subject 3>, and zips it closed. The entire video is accompanied by <Subject 1>'s inner monologue.
retention_analysis:
<Picture 1> (first frame of [Shot 1]): fully_preserved — the video uses <Picture 1> as the fixed background, with the tent interior environment, character posture, and item layout fully retained.
<Subject 1> (appears in [Shot 1]): fully_preserved — <Subject 1>'s appearance is derived from <Picture 1>, fully retained.
<Subject 2> (appears in [Shot 1]): fully_preserved — <Subject 2>'s appearance is derived from <Picture 1>, fully retained.
<Subject 3> (appears in [Shot 1]): fully_preserved — <Subject 3>'s appearance is derived from <Picture 1>, fully retained.
<Audio 1> (voice timbre reference for <Subject 1>): reference — <Subject 1>'s inner monologue references the vocal timbre and delivery characteristics of <Audio 1>, without copying the original signal.
detailed_description:
The target video adopts a cinematic photorealistic style, with an overall dim palette, illuminated by a warm light inside the tent, providing limited but warm lighting.
[Shot 1] The shot opens with <Picture 1> as the fixed background, with <Subject 1> sitting inside the tent, holding <Subject 2> and drinking water. After <Subject 1> finishing his water, <Subject 1> (S1) says in an off-screen voiceover: [Chinese] 不早了，赶快休息吧。 while <Subject 1>'s lips remain completely closed. In the mean time <Subject 1> puts the lid on <Subject 2>, places the cup into <Subject 3> beside him, and zips <Subject 3> closed.
overall_soundscape:
The lid of <Subject 2> produces a soft plastic or metal click as it is closed. The cup rubbing against fabric as it is placed into <Subject 3>, and the continuous clicking of zipper teeth as the backpack is zipped closed. Faint wind sounds can be heard from outside the tent. These ambient sounds continue throughout the video.
non_diegetic_music:
N/A