AI Content Studio · Video workspace
Ad Lab
Shape the picture. Plan the sound. Make the film.
Start with the VELUNE prompt, visual references and sound plan. Loading is free.
Opening project storage…
Connections
Choose your starting point
Picture & sound at a glance
Scene board
Review action, camera, attached references and intended sound together. Recipe timings start evenly spaced; VELUNE uses its supplied 24 fps edit. An imported prompt without shot data starts as one planning block. Board edits stay in this draft until you apply them to the prompt.
Scroll through the cut · select a shot to edit
Edit scene 1 · The finished product
Find the idea
Pick a concept
Ground the picture
Your product
The photo fills the fields below (brand read off the pack, a background color reasoned from the packaging) and grounds the video as its first frame.
Shape the story
The recipe · Reverse Rewind
The concept, deconstructed into the four things a video model actually reads. Edit any of it to make the concept yours.
Core aesthetics
- Top-down, overhead flat-lay. Static camera: zero panning or zooming.
- Snappy, high-contrast stop-motion aesthetic.
- Monochromatic ultra-bright single-color background; minimalist environment.
- Reverse-chronological timeline: finished product back to original packaging.
Sound design (rendered by Seedance 2.5 Reference)
- Rewind / reverse-playback whoosh distortion matching the reverse visuals.
- Utensil clinks and soft food movement, played backwards.
- Crisp cash-register ding synced to the price text appearing.
Action sequence
- 1 · The finished product: Fully prepared, plated item centered on the colored background.
- 2 · The removal: A human hand enters frame and pulls the plated item away.
- 3 · Deconstruction · toppings: A utensil scoops the topping off in fluid, reverse-gravity motion.
- 4 · Deconstruction · base: A second utensil lifts the base food upward and out of frame.
- 5 · Raw transformation: Cooked product snaps to raw state, flying backward out of the cooking vessel and sliding into its branded packaging.
- 6 · The product shot: A hand places the raw, packaged product flat against the background.
- 7 · Text overlay: Bold stark text snaps on: brand top-left, tagline middle-left, price bottom-right.
Text overlay
Brand name top-left, tagline middle-left, price bottom-right in bold, stark lettering, snapping on in sync with the final audio cue.
Guide the look & motion
References
Reference guide · Reverse Rewind · 2 important references missing
- 1Your product photo, shot straight-on with the label readable.still · Product identityDo this oneBecomes [Image1] and anchors identity. Everything else is judged against it.
- 2A second angle of the same product, from a three-quarter or side view.still · Product identityDo this oneTwo angles give the model geometry to hold onto. This is the single biggest reduction in drift.
- 3A 3-5 second clip whose camera move you want imitated.clip · Motion / cameraCamera language is far easier to show than to describe. Trim tight. The model reads the move, not the content.
- 4A photo of the product's prepared form, if you have one.still · Product identityThis concept ends on the raw pack but opens on the finished dish. Showing both halves stops the model inventing the food.
Order matters: references are numbered as you add them, and the prompt addresses them by that number. Add the product first.
Add from project assets
Use a saved packshot, Blender clip or audio take. Pending outputs are excluded. Adding a file does not start generation or change imported prompt tokens.
Should I upload a file or paste a URL?
Uploading and pasting a URL are different paths. An upload goes through fal's storage service, which needs separate permission from generation. A key that renders video can still be refused a file upload. A URL is handed straight to the model, so it needs no upload, no live mode and no storage access. It has to be a direct link to the file (ending in .mp4, .mov, .mp3…) that fal can reach without signing in.
For stills specifically, uploading is the more reliable path. An uploaded image is resized and carried inside the request itself, so nothing has to fetch it. A pasted image URL is fetched by the generation provider at render time. When that fetch fails, the provider does not report a missing file. It reports a content-policy violation about the imagery, which sends you looking for a problem in a picture that was never opened. Use Check references above before spending if your stills came from a URL.
Add more angles of the product to tighten the identity lock, a still to borrow a palette from, a short clip whose camera move and cut rhythm you want imitated, or a track whose beats the action should land on. Each gets a job in the prompt. Set it in the dropdown. Trim clips before uploading. These models read the camera move, not the content, so anything past a few seconds costs upload time and buys nothing.
Browse starter motion clips · optional
Abstract on purpose. The model reads a clip's camera move, cutting rhythm and energy and applies them to your product, so a reference with no subject in it has nothing to leak into the render except motion.
Vibrant churn
Continuous, fluid sweeping motion across tightly packed, chaotic clusters. Lively and playful, with no single fixed focal point. The elements constantly shift and churn. Point a product at this when it needs to feel highly creative, energetic, or bursting with variety. The wrong choice for minimalist, rigid, or highly serious branding.
Symmetrical pulse
Fixed-camera, hypnotic vertical rippling that pulses at a steady, driving rhythm. Strictly mirrored, pulling the eye down a central axis in repetitive, wave-like contractions. Ideal for audio gear, tech hardware, or anything that demands rigid synchronisation and a futuristic, beat-driven feel. Unsuitable for organic, unpredictable or free-flowing concepts.
Off-center vortex
A slow, creeping rotation that divides the frame, contrasting a solid block of colour against a swirling, suspended mixture. The camera feels like it is tracking a gentle, mechanical stirring motion with distinct floating elements. Use this for skincare, eco-friendly materials, or beverages where the product should feel balanced, mixed and carefully formulated.
Directional glide
A relentless, smooth, unidirectional wave travelling steadily across a dense, textured surface. Unbroken, undulating and velvety, conveying deep liquid progression with no abrupt stops or collisions. Apply this to luxury goods or hydration tech to grant the product a sleek, premium sweep. Too continuous and soft for fast-paced, high-impact edits.
Explosive bloom
A sudden, aggressive outward expansion from the centre that quickly decelerates into a slow, intricate crawl at the edges. The energy shifts dramatically from immediate, forceful impact to a lingering, highly detailed settling phase. Perfect for striking centre-frame product reveals, intense flavour drops, or dramatic transformations. The wrong choice for subtle, ambient or continuous background motion.
Choose the output
Format and cost
How this model uses references
Reference-to-video: each file has a position in the prompt ([Image1], [Video1], [Audio1]…). References guide identity and motion; review the result for drift.
How this is priced · 480×853 × 8s = ~$1.64
Seedance bills by token, not by second. Tokens ≈ width × height × seconds × 24 ÷ 1024, so pixel area matters as much as length. That is why the shape you pick changes the price as well as the crop: at the same resolution a 21:9 frame has more than twice the pixels of a 1:1 one. 1080p is also billed at a higher rate per token on top of having four times the pixels of 480p. Draft at 480p until the take is right.
Build the soundtrack
Sound
Seedance 2.5 Reference: Generates synchronized audio with the picture and accepts MP3/WAV audio references. A track can guide rhythm and mood; exact beat alignment is not guaranteed. Native audio has no extra Seedance generation charge.
ElevenLabs connection & audio delivery
Checking configuration…
Music, voiceover and sound effects use your existing fal connection. No separate ElevenLabs key is needed. This checks key presence; model access and balance are verified when you generate.
Plan before the render
Give every scene a sound.
Write the voice. Leave room to hear the product. Build a score around the moments that matter.
- 01 · Script & cues
- 02 · Audition voice
- 03 · Lock picture
- 04 · Score & mix
Start with a template. Its timings are editable; it does not inspect or rewrite your uploaded film.
Sound direction sent with the video
This block is appended to the video prompt, including imported Blender briefs. It changes sound instructions only. Silent mode also switches native audio off at the API where supported.
[Ad Lab sound direction] These instructions take precedence over earlier sound or music instructions only. Preserve all visual direction. Generate sound effects and ambience that fit the visible action. Preserve explicitly requested dialogue or voiceover from the brief; do not invent speech or singing. Musical direction: Playful indie-pop advertising bed at 128 BPM. Staccato muted electric guitar plucks, bouncy upright bass, offbeat hand claps, glockenspiel accents. Bright, quirky and warm. Clean confident ending on the downbeat. Instrumental, no vocals.
Spot effects · ElevenLabs Sound Effects v20 of 3 generated ·~$0.006 each
Optional sounds for the final edit, available with any sound mode. Describe one physical event per generation, audition it, then place it against the picture. These files are not automatically mixed into the MP4.
Rewind / reverse-playback whoosh distortion matching the reverse visuals.
Utensil clinks and soft food movement, played backwards.
Crisp cash-register ding synced to the price text appearing.
Generate one physical event at a time. Recipe effects and your added sounds are separate files to place against the action in your editor.
How the layers stack, and how to describe an effect
- Native audio is baked into the MP4; this workflow does not provide separate native stems. Switch native audio off (Silent) when you want the effects track entirely under your control.
- Spot effects arrive as separate files, one per effect. Nothing is placed for you: you drop each one on its frame in the edit, which is exactly the point. Placement is a decision, not a guess.
- Music is a third file, laid under both. On a model that reads audio in, it can also guide rhythm. See the timing reference above.
- Layered on top of native audio, a spot effect is a sweetener: it thickens the hit the model already made. Over a silent take it is the whole effects track.
Describing an effect
- Describe the physical event, not the feeling: “the metallic snap of a ring-pull, then carbonation hissing out” beats “refreshing can sound”.
- Name the material: glass, foil, kraft paper, brushed steel. Material is most of what a listener identifies.
- Say how close the mic is. “Close-mic’d, intimate, dry” gives you an ASMR hit; add “in a large room” and you get reverb baked in you cannot remove.
- One event per generation. Two effects in one prompt gives you a muddle of both; generate them separately and place them separately.
Set the direction
Compose the prompt
The recipe, your product fields and every reference job are compiled into one prompt, then polished for the target duration. Nothing is generated yet. Read it before you spend.
From direction to film
Generate
Before you spend $1.64
2 high-impact references are missing.
- Your product photo, shot straight-on with the label readable. Without a product reference the model invents the packaging outright.
- A second angle of the same product, from a three-quarter or side view. One angle leaves the model guessing at the sides and back, so the pack warps as the camera moves; this is the most common reason a take gets paid for twice.
Adding these costs nothing. Generating without them usually costs the price of a second take.
Seedance 2.5 Reference
8s · 9:16 · 480×853
Before you render: Upload the product photo ↗
Soundtrack finishing · no generation charge
Bring the film and sound together.
Your picture is one part. Shape the voice, music and effects into a finished stereo WAV, then listen with your video before handing it to your editor.
- 01 · Add takes
- 02 · Time & balance
- 03 · Listen & export
01 · Add your audio takes
0 added · 0 included in WAVGenerate or recover music, effects or scene voice above, then add those real takes here. Demo tones are excluded.
02 · Time & balance
8s soundtrackOpen a track to adjust its position, trim, level and fades. Existing scene timings are kept.
Ducking follows enabled voice clip windows, including silent pauses within each clip. 100 ms attack · 200 ms release. Audio ends at the cut; clips are never stretched or looped.
03 · Listen & export
Separate stereo WAVRender to hear your mix. The WAV contains the enabled tracks above. Combine it with the original video in your editor for the final MP4.