Video Prompt Builder
Format one shot brief into model-specific video prompts — references, shot timing, motion physics, and audio direction included
Turn a rough shot idea into a structured prompt formatted for Sora 2, Veo 3.1, Kling 3, Seedance 2, Wan 2.1, Hunyuan, or a universal portable target. The adapters are prompt-formatting targets: each one shapes syntax, durations, and reference limits for the model it names — none of them is a generation route. On Imgo, generation runs the model list that is live in Video Generator (today the Seedance family); for targets that are pending or discontinued, such as Sora 2, take the formatted prompt to wherever you run that model.
Capability snapshot
7
prompt-formatting targets
live
run on a live model you pick
audio
audio-aware direction
See Video Prompt Builder in action
A 27-second walkthrough of the workflow, the key benefits, and the results.
Core benefits
Practical value mapped to real production workflows.
Benefit
01
One brief, seven formatting targets
Start from one structured brief, then render it as a prompt formatted for Sora 2 (kept for formatting and migration — the model itself is discontinued), Veo 3.1, Kling 3, Seedance 2, Wan 2.1, Hunyuan, or a portable universal prompt.
Benefit
02
Keep motion, identity, and audio coherent
Specify weight, momentum, contact, secondary motion, appearance locks, dialogue timing, ambience, music, and sound effects instead of leaving critical behavior implicit.
Benefit
03
Hand off to a live model, guardrails first
Catch unsupported durations, overloaded references, timeline conflicts, and incomplete shot direction before you apply. The prompt and supported references land in Video Generator, where you pick from the live model list for the actual run.
Recommended workflow
A simple three-step path from source material to a reusable result.
Step 1
Anchor the shot and its references
Define the subject, setting, action, visual style, and any character, product, storyboard, scene, prop, video, or audio references.
Step 2
Direct motion, timing, and sound
Set camera movement, physicality, appearance consistency, shot-by-shot timing, dialogue, ambience, music, and sound effects.
Step 3
Validate, then run on a live model
Choose the formatting target and resolve capability or quality warnings. Applying carries the prompt and supported references into Video Generator, where you pick a live model; for a target Imgo does not run, copy the rendered prompt and use it wherever that model lives.
Frequently asked questions
Which video models does the builder format prompts for?
Seven targets: Sora 2, Veo 3.1, Kling 3, Seedance 2, Wan 2.1, Hunyuan, and a universal renderer for portable prompts. The adapters structure the prompt for a model's syntax and limits — they are not generation routes. The Sora 2 adapter stays for formatting and migration even though the model itself is discontinued.
Can I attach image, video, and audio references?
Yes. Assign each reference a purpose such as first frame, character look, storyboard, scene, prop, camera movement, motion rhythm, voice, or music. The handoff check shows what the selected formatting target can carry into the generator.
Does it handle shot timing and synchronized audio?
Yes. Build a non-overlapping timeline within the clip duration, override camera movement per segment, and place dialogue at the start, middle, or end alongside ambience, music, and sound effects.
Can I generate with Wan 2.1 or Hunyuan on Imgo?
No. Those adapters format the prompt for use wherever you run those models. Generation inside Imgo runs the models that are live in Video Generator at that moment — open its model list to see them, and pick one of those for the actual run.
Next step
Ready to use this feature in production?
Open the tool with a real image, compare the results, and keep the version that works.