The NYC Street Interview recipe is scenes you swap, not a new Omni board
/workflows/nyc-street-interview is a locked scene list. Recreate it; do not storyboard it again in Kling Omni.
/workflows/nyc-street-interview is a locked scene list. Recreate it; do not storyboard it again in Kling Omni.
The public recipe is three candid 9:16 street-vlog interviews at golden hour. Riley works three NYC corners with a handheld mic and one question: "What's the wildest thing you've ever done?" Kai, Maya, and Marco answer. That is a scene graph — prompts, references, model, durations — not a vibe. Opening Kling 3 Omni and asking for "six shots of a street interview" is a new film that happens to contain the word interview.
Three scenes, not six Omni cuts
The workflow object is specific:
- Aspect: 9:16
- Scenes: three, ten seconds each, thirty seconds of finished tape
- Cast: Riley (interviewer), Kai, Maya, Marco — locked character references, not "a girl in denim"
- Model on the recipe: Kling Video V3 Pro Image to Video
- Credit estimate: a flat 504 — 168 per scene, because the model line is the spend
Each scene is a pair: a still, then that still animated, then a stitch. Kai (OTS, subway story), Maya (OTS, bodega), Marco (two-shot, halal cart). Different corners on purpose. Same Riley. Same question. Native spoken dialogue in the prompts, not a VO pass you add later.
Recreate is not "make something like this." It is "materialise this graph." Read a workflow's credit estimate before you run it: scene count is not the bill. The video model is.
Recreate clones the graph. Omni invents a bumper.
Recreate a viral template is the agent verb: browse the public catalog, clone scenes, style, and model into your account, then run or remix. Cloning is free. Running is priced like the generation it is. You see the cost before anything dispatches. It is saved but not auto-run — swap the question, swap product stills, keep the cuts.
Recreate the workflow, not the screenshot is the same rule in conversion form. A screenshot of a street interview tells you the caption was big. It does not tell you the model, the stills, the scene list, or 504 credits.
Kling 3 Omni multi-shot is not Movie Mode is the other confusion. Omni takes one prompt and returns up to six distinct shots inside a single generation, usually a 15-second file. You still pay for seconds. Identities have to survive inside that generate. There is no scene planner, no chain off scene two's last frame, no combined 30-second export of three corners. You get one bumper with cuts in it.
Useful for a three-beat gag. Not useful for Riley-plus-three-strangers across three locations with locked refs. Omni restages. Restaging is drift. The workflow already named the people and attached their stills.
Swap the question. Keep the cuts.
Once the format works, the workflow is the product. Clone it. Change the line. Keep the OTS, the two-shot, the 10-second beats. Do not go back to an Omni storyboard every Monday because the last clip performed.
If the clip you care about is not in /workflows, you do not have a recipe. Build one: stills first, then I2V, then save your graph. Do not use Omni's six-shot syntax as a substitute for a scene list you never wrote.
FAQ
Is Recreate the same as generating "NYC street interview" in Omni?
No. Recreate clones the public workflow — three scenes, references, Kling Video V3 Pro I2V, 504 credits when you run it. Omni is one generate with internal cuts, typically ~15 seconds, up to six shots. Different objects. Different files.
Does cloning the NYC template spend the 504 credits?
No. Clone is free. Credits apply when you run it, at the cost shown before dispatch. Edit the question and swap assets while it is still a draft.
Can I use Omni under the hood and keep the three-scene structure?
Not as this recipe. Omni multi-shot lives inside one short generate. The NYC interview is three discrete I2V scenes with locked refs, stitched. Even if a scene happened to render on a Kling family model, the object is still the scene list, not Omni storyboard syntax.
Why is a 3-scene recipe 504 credits when longer recipes cost less?
Because the estimate is counting the video model, not the scene count. Kling Video V3 Pro Image to Video at 168 credits per scene is a different unit from a cheaper I2V row across fifteen scenes. Read the model line on the workflow page before you approve the run.