Seedance 2 on @TapNow_AI
Prompt:
**CAMERA:**
DV 16mm tape camcorder handheld feel. POV of CHASE holding the camera herself throughout each location, occasionally propped briefly for hands-free moments. Hand shake, misaligned framing, delayed focus pulls, clumsy zooms, occasional face cut-off framing, imperfect shots. Camcorder never appears on screen.
**LOOK:**
Soft, slightly blurry tape quality, faint tape noise, bloomed highlights, flickering auto-exposure, muted contrast, realistic skin tones — lighting shifts naturally per location (warm dorm light → cool van light → studio fluorescents → bright stage lights).
**STYLE:**
Fast-paced time-lapse montage feel — quick cuts stitched together across locations, sped-up transitional movement between them. Instead of synced dialogue, her voice plays as reflective voiceover narration over the visuals, tying the day together. Energy builds progressively from sleepy morning to high-adrenaline stage finish.
**Character**
CHASE — Korean idol, 20s. Long straight black hair, elegant yet lovely Korean features, dewy glass skin, coral pink lips, big eyes. Outfit changes naturally per location: cozy loungewear at the dorm, casual comfortable clothes in the van, modest athletic wear in the practice room, and a stage outfit for the final segment — each fully covering arms and torso.
**Setting Progression**
Dorm room (morning) → van interior (daytime) → practice room (afternoon) → backstage/stage (night).
**Storyboard (voiceover narration over visuals)**
1. *(~2s, dorm, propped camera, sleepy morning light)* She stretches, rubbing her eyes, hair messy. VOICEOVER (CHASE): "Every day starts the same way — way too early."
2. *(~2s, dorm, handheld, quick motion)* She moves through her morning routine in fast, sped-up cuts — brushing hair, grabbing a bag. VOICEOVER (CHASE): "Get ready, grab everything, and go."
3. *(~2s, van interior, handheld, window light)* She sits by the window, phone in hand, soft daylight passing over her face. VOICEOVER (CHASE): "The van's basically my second home at this point."
4. *(~1.5s, van, macro insert)* Close-up on her hand adjusting a playlist on her phone, light flickering through the window. No narration — ambient road sound only.
5. *(~2s, practice room, handheld, energetic)* She's mid-movement rehearsing choreography, camera catching quick glimpses of the mirror wall. VOICEOVER (CHASE): "Then it's hours of practice till my legs give out."
6. *(~2s, practice room, propped camera, water break)* She wipes sweat, drinks water, breathless but smiling. VOICEOVER (CHASE): "But somehow I never get tired of this part."
7. *(~2s, backstage, handheld, quick transition)* Hair and makeup blur past in quick cuts, staff moving around her, adrenaline building. VOICEOVER (CHASE): "And then suddenly, it's showtime."
8. *(~2s, stage, wide-to-close, high energy finish)* Bright stage lights, her silhouette stepping out as the camera catches a final glimpse before cutting to black. VOICEOVER (CHASE): "This is the part that makes all of it worth it."
China open-sourced a model that reconstructs any scene in 3D from a regular video, in real-time.
one camera. no LiDAR. 10,000+ frames without falling apart.
just walk around with your camera and watch the entire world get rebuilt in 3D at 20 fps.
→ runs at ~20 FPS on a single GPU
→ Stable over 10,000+ frames
→ Beats optimization-based methods on benchmarks
→ Works on drone footage, driving videos, indoor walkthroughs
100% open source.
DEJA DE PROMPTEAR. EMPIEZA A LOOPEAR.
Encontré una web que recopila los loops más usados por la comunidad
→ https://t.co/lX59LpOV2r
Los propios creadores de Claude Code lo dicen: el futuro no es promptear, es diseñar loops.
No sabes qué son ni cómo crearlos?
En este articulo te lo explico en detalle👇
D-20 Dice Turntable:
The reference had this nice anisotropic flow structure inside of it. Recreating it I went the physical route with a million small strands swirling inside of the dice. Not really efficient, but a prove of concept.
@OTOY@MaxonVFX@Maxon_Cinema4D#c4d#octane