The Viral Panel & Reaction Reel recipe is scenes you swap, not a new Omni board
/workflows/viral-panel-reaction-reel is a locked scene list. Recreate it; do not storyboard it again in Kling Omni.
/workflows/viral-panel-reaction-reel is a locked scene list. Recreate it; do not storyboard it again in Kling Omni.
The public recipe is a four-scene 9:16 hook: a professional panel expert discusses before/after results with a product, denying she is gatekeeping; then an influencer films a selfie-POV reaction, holding the product and confirming the claim. That is a scene graph — prompts, references, model — not a vibe. Opening Kling 3 Omni and asking for "six shots of a panel reacting to a product" is a new film that happens to contain the word panel.
The graph is four scenes and three assets
The workflow object is specific:
- Aspect: 9:16
- Scenes: four. Scenes 1–2 are the expert on a modern panel stage, tailored navy blazer, microphone, professional lighting. Scenes 3–4 are the influencer in a bright cozy bedroom, casual white knit, product in hand, selfie-POV.
- Cast and product: Expert, Influencer, Product — locked references, not "a woman on a stage."
- Model on the recipe: Seedance v1.5 Pro Image to Video
- Credit estimate on the card: 60 / 120 full
- Chain: each scene is independent. This is a stitch of four I2V takes, not a last-frame walk from the stage into the bedroom.
Style on the recipe: cinematic photoreal, 9:16; panel scenes documentary-stage; reaction scenes selfie-ring-light vlog; wardrobe holds across each character's pair.
Recreate is not "make something like this." It is "materialise this graph." 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 product stills, keep the cuts.
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. Identities have to survive inside that generate. There is no scene planner, no chain off scene two into a bedroom, no combined export of a stage plus a vlog. You get one bumper with cuts in it.
Useful for a three-beat gag. Not useful for an expert-plus-influencer across two rooms with locked refs. Omni restages. Restaging is drift. The workflow already named the people, named the product, and attached their stills.
Swap the SKU. Keep the cuts.
Once the format works, the workflow is the product. Clone it. Change the line. Keep the panel pair and the selfie pair. Do not go back to an Omni storyboard every Monday because the last clip performed.
The remix that belongs here: new product still on the product asset, same expert and influencer refs, same four-beat. The remix that does not: "same energy, new storyboard, six Omni cameras."
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 "viral panel reaction" in Omni?
No. Recreate clones the public workflow — four scenes, expert / influencer / product refs, Seedance v1.5 Pro Image to Video, 60 / 120 credits when you run it. Omni is one generate with internal cuts, typically ~15 seconds, up to six shots. Different objects.
Does cloning the Viral Panel template spend the 60 credits?
No. Clone is free. Credits apply when you run it, at the cost shown before dispatch. Edit the lines and swap assets while it is still a draft.
Can I use Omni under the hood and keep the four-scene structure?
Not as this recipe. Omni multi-shot lives inside one short generate. The panel reel is four discrete I2V scenes with locked refs, stitched, two rooms.
Why is a 4-scene recipe 60 credits when a 3-scene street interview costs more?
Because the estimate is counting the video model, not the scene count. Seedance v1.5 Pro Image to Video on this card is a different unit from a dearer I2V row. Read the model line on the workflow page before you approve the run.