I'm trying to understand how the new v2.0 Studio workflow is intended to handle music-video editing compared with the previous manual workflow. For an example, I'll use 30-seconds music audio track. My source audio might be 30 seconds, but creatively I may want 4–6 completely different scenes during those 30 seconds.
For example:
0:00–0:06 — Woman singing on apartment couch
0:06–0:11 — Woman walking through hallway
0:11–0:20 — Woman singing beside the pool
0:20–0:30 — Woman walking outside in the rain
Those scene lengths should be determined by the song/lyrics/beats, not by LTX's maximum generation-window length.
Previously I could work around this in Studio Manual by rendering individual ~10-second clips: give each clip its own start image, prompt and matching section of audio, leave some leading/trailing room, regenerate individual clips when necessary, then assemble everything in Resolve.
In v2.0 I'm having trouble reproducing that workflow. Auto keeps my 30-second audio duration but decides it only needs 2 generation windows. Window mode lets me request more windows, but then it increases the total generated duration beyond the source audio. Manual says each non-empty prompt line corresponds to a window, so with Auto choosing only 2 windows I seemingly only get direct control over 2 window prompts.
What I'm looking for is shot/scene planning independent of generation-window count: keep the source song at exactly 30 seconds, let me define as many scenes/shots as I want within that duration, assign each scene its own start/reference image and prompt, and give each scene an exact or AI-planned duration based on lyrics/beats. Maestro could then determine whatever underlying LTX/H3 windows are necessary to render those shots.
Is that workflow currently possible in v2.0? If not, could Studio/Director support a fixed-audio / variable-shot timeline where scenes have their own prompts, images and in/out times without changing the duration of the source song?
We used to be able to write long prompts per window/scene/image, but now it is like one line per window, which is not enough to describe what I want.
AboutMaestroBlizaine/Maestro
I'm trying to understand how the new v2.0 Studio workflow is intended to handle music-video editing compared with the previous manual workflow. For an example, I'll use 30-seconds music audio track. My source audio might be 30 seconds, but creatively I may want 4–6 completely different scenes during those 30 seconds.
For example:
0:00–0:06 — Woman singing on apartment couch
0:06–0:11 — Woman walking through hallway
0:11–0:20 — Woman singing beside the pool
0:20–0:30 — Woman walking outside in the rain
Those scene lengths should be determined by the song/lyrics/beats, not by LTX's maximum generation-window length.
Previously I could work around this in Studio Manual by rendering individual ~10-second clips: give each clip its own start image, prompt and matching section of audio, leave some leading/trailing room, regenerate individual clips when necessary, then assemble everything in Resolve.
In v2.0 I'm having trouble reproducing that workflow. Auto keeps my 30-second audio duration but decides it only needs 2 generation windows. Window mode lets me request more windows, but then it increases the total generated duration beyond the source audio. Manual says each non-empty prompt line corresponds to a window, so with Auto choosing only 2 windows I seemingly only get direct control over 2 window prompts.
What I'm looking for is shot/scene planning independent of generation-window count: keep the source song at exactly 30 seconds, let me define as many scenes/shots as I want within that duration, assign each scene its own start/reference image and prompt, and give each scene an exact or AI-planned duration based on lyrics/beats. Maestro could then determine whatever underlying LTX/H3 windows are necessary to render those shots.
Is that workflow currently possible in v2.0? If not, could Studio/Director support a fixed-audio / variable-shot timeline where scenes have their own prompts, images and in/out times without changing the duration of the source song?
We used to be able to write long prompts per window/scene/image, but now it is like one line per window, which is not enough to describe what I want.