The NEURA — Coffee vs Brain recipe is scenes you swap, not a new Omni board
/workflows/neura-coffee-vs-brain is a locked scene list. Recreate it; do not storyboard it again in Kling Omni.
/workflows/neura-coffee-vs-brain is a locked scene list. Recreate it; do not storyboard it again in Kling Omni.
The public recipe is an AI anime explainer: caffeine as golden heroes, adenosine as purple blob-monsters, a tiny neuron-city, a branded NEURA bag and mug. Eighteen clean clips. That is a scene graph — prompts, reference stills, model, durations, voiceover — not a vibe. Opening Kling 3 Omni and asking for "six shots of coffee versus the brain" is a new bumper that happens to contain the word coffee.
Eighteen scenes, not six Omni cuts
The workflow object is specific:
- Aspect: 9:16
- Scenes: eighteen, five seconds each
- Model on the recipe: Vidu Q3 Image to Video
- Credit estimate: 702 / 1,386 — the two published figures on the recipe, because the video model is the spend
Each scene is a pair: a still, then that still animated, then a stitch. The locked list is the product: branded opener (mug + kraft bag, steam only), sleepy neuron-blobs, adenosine at the docking port, city lights out, the kitchen sip, the golden coffee wave, caffeine heroes at the docks, purple fading, fireworks, the wide-awake man, the end card. Different rooms on purpose. Same brand stills. Voiceover is a line per scene, not a VO you invent later in Omni.
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 bag stills, swap the VO brand line, 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. You still pay for seconds. Identities have to survive inside that generate. There is no scene planner, no chain off scene four's last frame into a new neuron-city, no eighteen-clip combined export, no per-scene VO slot. You get one bumper with cuts in it.
Useful for a three-beat gag. Not useful for mug → brain-city → sip → wave → docks → end card with locked refs. Omni restages. Restaging is drift. The workflow already named the beats and attached their stills. Every scene on this recipe says the same motion contract: use the attached still; only the named action moves; camera stays still; no new characters. That is I2V discipline. Omni's six-camera storyboard is the opposite instruction.
Swap the bag. Keep the cuts.
Once the format works, the workflow is the product. Clone it. Change the kraft still to your SKU. Keep the 5-second beats, the sleepy-blob, the docking-port lock, the end card. Do not go back to an Omni storyboard every Monday because last week's coffee explainer 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 "coffee vs brain" in Omni?
No. Recreate clones the public workflow — eighteen scenes, references, Vidu Q3 Image to Video, 702 / 1,386 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 NEURA template spend the 702 credits?
No. Clone is free. Credits apply when you run it, at the cost shown before dispatch. Edit the VO and swap bag stills while it is still a draft.
Can I use Omni under the hood and keep the eighteen-scene structure?
Not as this recipe. Omni multi-shot lives inside one short generate. NEURA is eighteen discrete I2V scenes with locked refs, stitched, plus a voice line per scene. 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 an 18-scene recipe 702 credits when a 3-scene interview can cost 504?
Because the estimate is counting the video model, not the scene count. Vidu Q3 Image to Video across eighteen five-second scenes is a different unit from Kling Video V3 Pro I2V at a much higher per-scene rate. Read the model line on the workflow page before you approve the run.