ComfyUI Node
H3 Prompt Writer π
Type what happens, one line for each moment, and leave a blank line to cut to a new place. Connect up to four pictures, give each one a job such as person, place or outfit, and name them @1 and @2 in your lines. Connect a video to copy its moves or carry it on. Add a voice or a song and it writes the lines H3 needs. H3's own six parts go through as they are. Connect a small text model and it fills in a one-line idea.
H3 Prompt Writer π
- clip
- picture_1
- picture_2
- picture_3
- picture_4
- video
- video_sound
- voice
- song
- prompt
- picture_1
- picture_2
- picture_3
- picture_4
- video
- video_sound
- voice
- song
- song_under
- frames
- width
- height
βscriptβΊ
βseconds8βΊ
βcameraas typedβΊ
βlookfrom the pictureβΊ
βsong_start0.0βΊ
βcut_on_beattrueβΊ
βlanguageEnglishβΊ
βjob_1personβΊ
βjob_2personβΊ
βjob_3personβΊ
βjob_4thingβΊ
βvideo_jobcopy its movesβΊ
Categoryπ AusBoss/Utility
Inputs (21)
| Name | Type | Default | Description |
|---|---|---|---|
| script | STRING | What happens, one line for each moment. A blank line cuts to a new place. @1 is Picture 1. Start a line with 3s: to put it on that second. | |
| seconds | INT | 85β15 | How long the clip is. Plan on about one moment a second at most. |
| clipopt | CLIP | Optional: a small text model such as Qwen3-VL 8B. It adds moments after a one-line idea and matches the sound to the place. | |
| picture_1opt | IMAGE | Your first picture. Type @1 to name it in a line. | |
| picture_2opt | IMAGE | Optional: a second picture, with its own job. Type @2 to name it. | |
| picture_3opt | IMAGE | Optional: a third picture, with its own job. Type @3 to name it. | |
| picture_4opt | IMAGE | Optional: a fourth picture, with its own job. Type @4 to name it. | |
| videoopt | IMAGE | Optional: the frames of a video. Pick what it is for under Video does. | |
| video_soundopt | AUDIO | Optional: the video's own sound. Only keep going uses it. | |
| voiceopt | AUDIO | A clip of the voice to use, about 10 seconds. | |
| songopt | AUDIO | The music to use. Each moment moves onto its beat. | |
| cameraopt | COMBO | as typed | How the camera moves the whole way through. As typed leaves it to your words. |
| lookopt | COMBO | from the picture | From the picture keeps your photo's look. The others redraw it in that style. |
| song_startopt | FLOAT | 0.00β86400 | The second of the song to start from, so the clip gets the good part. |
| cut_on_beatopt | BOOLEAN | true | Moves each moment onto the nearest beat of the song. Pick off to keep your own seconds. |
| languageopt | STRING | English | The language of the words in quotes. |
| job_1opt | COMBO | person | What this picture is for. Person goes wherever your lines say. Place is where it happens. Outfit and thing work best with nobody in the picture. Style gives only the look. Start on it and end on it fix the first or last moment. |
| job_2opt | COMBO | person | What this picture is for. Person goes wherever your lines say. Place is where it happens. Outfit and thing work best with nobody in the picture. Style gives only the look. Start on it and end on it fix the first or last moment. |
| job_3opt | COMBO | person | What this picture is for. Person goes wherever your lines say. Place is where it happens. Outfit and thing work best with nobody in the picture. Style gives only the look. Start on it and end on it fix the first or last moment. |
| job_4opt | COMBO | thing | What this picture is for. Person goes wherever your lines say. Place is where it happens. Outfit and thing work best with nobody in the picture. Style gives only the look. Start on it and end on it fix the first or last moment. |
| video_jobopt | COMBO | copy its moves | What the video is for: copy its moves, swap the person in it, keep it going, or give it a new voice. Swap and new voice ignore Seconds and keep the video's length. |
Outputs (13)
| Name | Type | Description |
|---|---|---|
| prompt | STRING | The finished prompt. Wire it into H3's prompt. |
| picture_1 | IMAGE | Your pictures in the order the prompt counts them. Wire it into H3's first ref_image. |
| picture_2 | IMAGE | The next picture. Wire it into H3's second ref_image. Empty when there is no such picture. |
| picture_3 | IMAGE | The next picture. Wire it into H3's third ref_image. Empty when there is no such picture. |
| picture_4 | IMAGE | The next picture. Wire it into H3's fourth ref_image. Empty when there is no such picture. |
| video | IMAGE | The video, or only its end to keep going from. Wire it into H3's first ref_video. |
| video_sound | AUDIO | The video's sound, when it should reach H3. Wire it into H3's first ref_video_audio. |
| voice | AUDIO | The voice, 15 seconds at most. Wire it into H3's first ref_audio. |
| song | AUDIO | The song, cut to the clip. Wire it into H3's next ref_audio. Empty when a voice is connected too. |
| song_under | AUDIO | With a voice and a song, the song to mix under the finished clip's sound. Wire it into Audio Merge. |
| frames | INT | The clip's length in frames. Wire it into H3's length. |
| width | INT | The width of your video, or else of your first picture. Wire it into H3's width. |
| height | INT | The height of your video, or else of your first picture. Wire it into H3's height. |