Shot-faithful templates
Three scenes follow the original structure beat for beat — the finale, the vocal close-up, the keys.
AI video generator
Outstanding AI Video Generator
The viral Tiny Desk meme is the last 19 seconds of "Outstanding". Pick the shot you want to front, upload one photo, and the AI casts you into the band.
- Buy once, generate for 12 months
- No watermark on paid packs
- Renders in about 2 minutes
- 16:9 scenes · crop to 9:16 in one step
Studio
Outstanding studio
Pick a scene, drop in one or two photos, and the band takes it from there.
Scene
Lead performer
Second band member
OptionalOptional — replaces the second figure in the scene.
Prompt (fixed for this scene)
@Image1 defines CHARACTER_1. Use CHARACTER_1's image-defined face, anatomy, proportions, clothing and accessories. Replace exactly one fixed source target. TARGET_1 is the lead singer: the man who sings directly into the vintage condenser microphone on the desk, frontmost of the four-man band in the closing shots (gray hair under a light-coloured cap). Replace only TARGET_1 with CHARACTER_1. Lock the mapping through every shot. Never swap characters or replace the instrumentalists. FULL APPEARANCE REPLACEMENT: erase the original singer's face, eyes, nose, mouth, ears, skin, hair, body and clothes. No source-face remnants, facial blending or reversion. The uploaded image alone determines the new appearance. PERFORMANCE LOCK: replicate the singer's actions and expressions at source timing. Preserve lip movements, mouth opening and closing, smiles, glances, head tilts, leans toward the microphone, and every hand and torso gesture at the exact source moments. Match mouth shapes, eyes, jaw motion and body rhythm. Do not invent movements. SET PRESERVATION: keep the source video's entire visible set identical in every shot — the tiny desk, vintage microphone, red mixing console, instruments, props, packed bookshelf wall, warm tungsten lamp glow, colour grade and film grain. Add nothing, change nothing. OUTPUT PRESERVATION: preserve the source shot order, framing, camera moves, focus, cuts, timing, duration and musical performance. Adapt the character's image-defined anatomy naturally to the source actions. No extra people, deformed limbs, flicker, floating props or set changes between shots.
Opens the generator with your prompt, model and photo ready to go.
The four scenes
Posters from the scene plates; your face takes the stage next.
What is the Outstanding AI video?
An AI-generated video that recasts the final 19 seconds of Charlie Wilson's June 2023 tiny desk performance of "Outstanding" with faces from uploaded photos — lead vocal at the desk mic, an alto-sax cutaway, and the full-band finale in front of the bookshelf.
Why this generator nails it
Two chairs, two photos
Photo 1 takes the featured performer; photo 2 can cast a friend on sax or keys in the same render.
One pack video per render
The 19-second finale costs the same single video as a 5-second cutaway. No subscriptions.
Make your Outstanding video in 3 steps
Step 01
Choose your shot
Finale, vocal, or keys — each scene is pre-timed to the original edit.
Step 02
Upload the faces
One photo for the featured performer; add a second to cast the bandmate.
Step 03
Generate and post
Rendering takes about two minutes; the clip lands ready for TikTok and Reels.
The 19-second shot breakdown
The meme's three-beat structure, timed from the original clip.
| Time | Shot | What happens |
|---|---|---|
| 0–6.75s | Shot 1 — Lead vocal | The singer leans into the desk microphone and rides the hook. |
| 6.75–11.75s | Shot 2 — Sax solo | Cutaway to the alto sax taking the solo, brass in the amber light. |
| 11.75–19s | Shot 3 — Full band finale | Vocal, sax and the red keyboard finish together in front of the bookshelf. |
Photo guide for the three chairs
Front-facing, well-lit, one face per photo. A few pointers per chair:
Lead vocal
Eyes visible, mouth free — the close-up leans into the mic, so frame from the chest up.
Sax solo
The cutaway is mid-shot, so any angle works; hair and skin tone carry the identity.
Red keyboard
Hands do the talking here — the face stays in frame above the crimson keys.
Prompts for the Outstanding trend
Working reference-to-video prompts — copy, swap the face, generate.
Full band finale
The final 19 seconds of a tiny desk concert: the singer steps to the desk microphone for one last run of the hook, an alto sax takes a short solo, and the whole band finishes together in front of the bookshelf. Warm tungsten lamps, crimson red keyboard, 35mm film grain. @Image1 is the lead singer, @Image2 the sax player.
Lead vocal close-up
A tiny desk concert close-up: the lead singer leans into a vintage condenser microphone, eyes closed mid-note, singing the hook full-voice. Blurred bookshelf bokeh, warm tungsten rim light, soft film grain. Replace only the singer with @Image1.
Sax cutaway
A tiny desk concert cutaway: an alto saxophonist takes a solo, fingers on the pearl keys, brass gleaming under the amber spotlight, head back on the high note. Bookshelf wall softly blurred. Replace only the saxophonist with @Image1.
Red keyboard comp
A tiny desk concert shot: a keyboardist comps bright chords on a crimson red electric keyboard, grinning on the fill, bookshelf wall and tungsten lamps behind. Replace only the keyboardist with @Image1.
Stage modifier pack
Append to any prompt: packed bookshelf wall, warm tungsten desk lamps, vintage condenser microphone, deep walnut shadows, soft 35mm film grain, intimate club atmosphere.
Identity lock
Keep everything else unchanged: staging, framing, lighting, colour grade and the timing of every beat. Do not copy the face of the performer you replace — use the reference photo. No text, captions, logos or watermarks.
Outstanding AI video — FAQ
- What are the 19 seconds of the Outstanding meme?
- The closing run of Charlie Wilson's tiny desk "Outstanding": lead vocal at the desk mic (0–6.75s), alto-sax cutaway solo (6.75–11.75s), then the full band — vocal, sax, red keyboard — finishing together (11.75–19s).
- How many faces can I cast at once?
- Two per render: the featured performer (photo 1) and one bandmate on sax or keys (photo 2). The rest of the band comes from the scene plate.
- Does the video keep the music?
- The 19-second finale engine preserves the plate's own soundtrack, so the beat is built in. The cutaway scenes generate their own audio bed.
- What photo works best?
- A clear, front-facing photo with even lighting — one face, no sunglasses for the vocal chair. Chest-up framing gives the close-up the most to work with.
- How long does a render take?
- About two minutes for every scene, long or short. Failed renders refund their credits automatically.
- Can I use the clips commercially?
- Yes — every paid-pack render is watermark-free and cleared for commercial use.
More generators & templates
All-Loss Coaches Tiny Desk
Cast your coaching staff into the All-Loss Tiny Desk meme. Five chairs, one headset, zero wins — built from your photos in about two minutes.
Cast my coaching staffUsher "Watch This" Meme
Recreate Usher's "Watch This" tiny desk intro with any face. The point-to-camera beat, the sunglasses, the smirk — one photo, about two minutes.
Make my "Watch This"Tiny Desk AI Prompts
25+ working prompts for the tiny desk meme: full band cast, per-shot scenes, stage modifiers, and a free FFmpeg path for CapCut-free edits.
Run the prompt hereReady for your tiny desk debut?
One photo, one scene, one clean clip. The trend moves fast — get your take up tonight.
Generate my Outstanding video