underwood

@underwoodxie96 • 37,982 subscribers

Sharing AI prompts, workflows & tips. Backup: @promptsref DM for collaborations.

Shorts

I made a second version of the transformation video. This time I moved the character into a real environment instead of using a plain white background. I also changed the opening and showed the final transformation result first. The overall flow feels much stronger now. Full workflow + prompts: The interesting part is that this type of video is much easier to make than it looks. You only need a base image, then generate the next keyframe through simple edits or outfit changes on the canvas. The entire transformation sequence is built from those keyframes.

102,161 görüntüleme

I made a second version! This time, I improved the opening to make it more eye-catching, added extra padding to the character shots so the video won’t get cropped across different social platforms, and updated the prompt into English. I also improved the canvas workflow. Previously, I had to generate multiple images and videos one by one, then pick the best results. Now the canvas supports generating multiple results in a single run, which has greatly improved my workflow efficiency. Now you only need to swap the image, and the same video prompt can still produce great results. Which anime cosplay should I make next? Full workflow and prompts:

161,925 görüntüleme

Version 3 is here. The character actions are much more ambitious this time, which also makes generation more challenging. Expect to run a few generations before landing the perfect result, but the payoff is worth it. Fork the workflow and show me what you create. 🚀

37,586 görüntüleme

Thanks to seedance 2.0, They were relieved of their suffering.

621,792 görüntüleme

I combined several recent trending video elements to create the video below, and the result turned out to be surprisingly fun. I think Seedance 2.0 is especially good for creating this kind of “only-exists-in-your-imagination” style video. I also shared another version of the video along with the full production workflow in the comments.

45,978 görüntüleme

test GPT 2.0 + Grok I don't even need to type a prompt.

95,128 görüntüleme

I think you'll like this dance.

415,373 görüntüleme

One trick we discovered for avoiding realistic face moderation issues in Seedance 2.0 is using character turnaround sheets (front / side / back views). The first video is one of our experiment results — and it runs successfully. We’ve now integrated character turnarounds directly into our workflow + canvas system: 1. If your artwork was generated on our site, you can drag the image into the canvas directly from the Assets tab 2. Click the “Character Turnaround” button above the image to automatically generate a 3-view turnaround sheet 3. Create a new video node and use the turnaround sheet directly with Seedance 2.0 inside the workflow I’ve shared the workflow link in the comments if you want to explore the exact prompts, setup, and workflow details.

30,029 görüntüleme

It would be better if the voice sounded a little better.

46,676 görüntüleme

How I made the video below (17s): 1. Use Nano Banana to generate keyframes (a consistent world + full environment) 2. Use Kling with first/last frame reference to generate the in-between shots (bring the keyframes to life) 3. Use CapCut for revisions and editing (pacing, transitions, SFX, subtitles) There are three main challenges: 1. Getting AI to produce story-driven visuals: you need to bake relationships and narrative intent into the prompt 2. Writing prompts in cinematic language: specify shot types, camera movement, and framing changes to make transitions smoother 3. Editing is the real “ceiling”: assembling shots, controlling rhythm, building emotion, and syncing sound with visuals all come down to editing Making AI shorts is basically a hybrid job: writer-director + editor. If you understand storytelling and camera grammar—and then cut it with the right rhythm—the results get dramatically better.

303,820 görüntüleme

Rita AI now supports Seedance 2.0. If you're looking for a platform that combines AI image generation, AI video generation, and workflow orchestration, this one is worth checking out. In addition to Seedance 2.0, it also supports Kling 3.0 and Motion Control, making dynamic camera moves, controllable motion, and video generation much easier. Link: I tested it with the following prompt, and the result felt very cinematic: A fearless young woman rides a skateboard at high speed through the crowded streets of New York City, weaving through pedestrians, darting past street vendors, yellow taxis, and cyclists with breathtaking agility. She rockets through intersections, skims past towering skyscrapers and iconic storefronts, and launches over curbs, street cracks, and scattered obstacles with stylish precision. Every movement feels bold, controlled, and exhilarating. Shot like a cinematic action sequence, the scene features fast-paced tracking shots, dramatic low-angle close-ups of the skateboard wheels scraping the asphalt, sweeping side-follow shots, and occasional slow-motion hero moments as she lands tricks and cuts through traffic. Dynamic motion blur heightens the sensation of speed, while golden hour sunlight bathes the city in a warm glow, reflecting off glass facades, metal surfaces, and the street below. Steam drifts from subway vents, traffic lights flicker, and the soundless visual energy of New York creates a pulsing urban backdrop. Ultra-realistic, intense, stylish, and immersive, with the visual tone of a high-end action film, capturing speed, confidence, danger, and freedom in the heart of the city.

61,800 görüntüleme

seedance 2.0 Crazy McDonalds

81,919 görüntüleme

seedance 2.0 Our website is now live. prompt： Theme: The final play in the atmosphere of the NBA Finals, a superstar's step-back three-pointer for the game-winning shot. Duration: 15 seconds. Frame: 9:16. Vertical screen. Style: Ultra-realistic sports live broadcast + cinematic bullet time replay of key moments. Core principle: Like a live broadcast, not a game, not a commercial studio shoot. 15-second storyboard: 0.0s - 2.5s Close-up sideline shot, the protagonist dribbles the ball at a 45-degree angle on the right side. The arena is packed, with a real score bar and countdown at the top. The camera shakes slightly, like a handheld stabilizer used with a telephoto lens for broadcasting. The rubbing of shoes and the suppressed cheers of the crowd can be heard. 2.5s - 5.0s The defender closes in, the protagonist dribbles and changes direction repeatedly, probing with his shoulder, the physical contact is obvious. The camera zooms in on the dribbling area above the chest and waist, sweat, breathing, and jersey movements are clearly visible. The basket remains visible in the upper part of the frame. 5.0s - 7.0s The protagonist suddenly stops and steps back, creating half a step of space. The timer has only 2 to 3 seconds left. The commentator's volume rises, and the audience begins to stand. This is a build-up of emotion, no slow motion. 7.0s - 8.5s: Jump and release, entering bullet time. The camera circles in a semi-circle from the protagonist's side and front, moving at an extremely slow speed. Focused close-ups: fingers flicking the ball, beads of sweat hanging in the air, jersey fibers, shoe soles leaving the ground, audience flashes, the backboard and lights creating a strong sense of spatial depth. 8.5s - 10.5s: Instantly returning to normal speed, the basketball arcs high towards the basket. The camera zooms in slightly, the net, rim, and scoreboard all in focus. The sound effects tighten, briefly lowering the ambient noise to make the basket more impactful. 10.5s - 12.0s: Swish through the net, the "swish" of the net is very clear, the buzzer sounds almost simultaneously. The score changes, the commentator explodes, the audience erupts. 12.0s - 15.0s: The protagonist lands, turns around, and roars or spreads his arms in celebration; teammates rush over, the audience erupts in cheers, and cell phone flashes fill the screen. The camera then switches back to a live broadcast style, retaining a slight sense of compression and the chaotic atmosphere of the scene, like capturing the actual moment after the match.

33,358 görüntüleme

I didn’t expect Grok’s video model to improve this much. Today, when I was generating a video with Seedance 2.0, I found the results weren’t very good. So I tried using the exact same source material and prompt in Grok instead. To my surprise, Grok actually produced better results than Seedance 2.0. I’ve put the prompt and source material in the comments, so if you’re interested, you can give it a try too. The left side shows the video generated by Grok, and the right side shows the video generated by Seedance 2.0.

33,245 görüntüleme

Seedance 2.0 is now live on our website. ⚠️ Warning: The following video is extremely unsettling. If you’re sensitive to horror content, consider watching without sound or skipping it. prompt： one-take cinematic horror scene, old apartment hallway at night, one young woman holding a phone light, slow tracking shot, tense silence. first step: ceiling light suddenly goes out, brief blackout, light returns, hallway seems normal. second step: light goes out again, slightly longer blackout, faint strange sound, light returns, bathroom door is now more open, her breathing becomes faster. third step: she hesitates in fear, then takes one more step, longest blackout, eerie low laugh in darkness, light snaps back on, a pale inhuman figure is suddenly standing motionless directly in front of her face, intense dread, cut to black. realistic, oppressive, restrained, psychological horror, cold green and dirty yellow lighting, shallow depth of field, film grain, high-end horror movie quality.

19,341 görüntüleme

$We have released Seedance 2.0. Due to the 2500-character limit, please translate the following prompts into Chinese before use. [Technical Specs] Generate a 10-second, 16:9, 720p cinematic video. Smooth continuous camera motion with no cuts. The overall pacing is fast and tightly compressed, with rapid escalation from start to finish. Audio evolves quickly from a high-performance engine idle into intricate mechanical shifting and clicks, culminating in a soft electronic chime and the distinct sound of a "mwah" blowing kiss. [Global Constraints] Only the evolving mechanical character appears; no other humans or characters. All transformations must follow physical logic and maintain structural continuity. No object should pass through or intersect with other solid objects. Every robotic component must originate from visible parts of the Porsche 911 (doors, hood, wheels, chassis) through unfolding, splitting, or reconfiguration. [Scene Setup — 0:00–0:01] A sleek, metallic silver Porsche 911 sits on a rain-slicked futuristic city street at night, neon lights reflecting off its polished surface. The camera starts at a low-angle front-quarter view and begins a fast, smooth tracking-arc towards the side. [Rapid Transformation Initiation — 0:01–0:03] Transformation triggers instantly. The car’s suspension drops, and the frame begins to fracture into a complex grid of panels. The doors swing open and begin to segment into articulated arm structures. The front hood splits down the center, folding inward to reveal a glowing internal core. The headlights flicker and start to reorient as the "eyes." [Accelerated Feminine Reconfiguration — 0:03–0:07] The mechanical action is dense, overlapping, and fluid, emphasizing graceful but powerful motion. Lower Body: The rear wheels and wheel arches split and rotate downward, reassembling into slender, high-heeled mechanical legs. Torso: The roof and rear engine cover slide and compress, forming a sleek, curvaceous hourglass torso that retains the car’s aerodynamic lines. Arms & Hands: The side mirrors and door panels unfold into delicate but strong hands and fingers. Head: The front bumper and emblem area segment and rise, folding into a feminine-shaped head with a sleek metallic "helmet" visor. [Logical Transformation Constraints — No Spontaneous Appearance] The robot’s "skin" is composed of the car's outer silver panels. The internal frame and wiring emerge from the engine and undercarriage. No parts appear out of thin air; every joint is a reconfigured automotive component. [Transformation Completion — 0:07–0:08.5] The robot stands tall and elegant. The silver panels lock into place with a satisfying "click," revealing glowing blue LED accents in the seams. The silhouette is clearly feminine, humanoid, and sophisticated, reflecting the premium design of the original vehicle. [Final Hero Ending — 0:08.5–0:10] As the robot stabilizes, the camera performs a rapid, smooth zoom-in (Dolly-In) directly to her face. The robot tilts its head slightly, and the optic sensors (eyes) brighten. It brings its mechanical hand to its metallic lips and performs a graceful blowing kiss (fly-kiss) gesture toward the camera. The video ends with a close-up of the face, capturing the reflection of neon lights in its visor just as the kiss is released. [Cinematography Notes] Continuous Motion: No cuts or fades; the camera must transition from the car-tracking shot to the face-zoom seamlessly. Material Consistency: The robot must maintain the exact metallic silver paint, texture, and reflections of the Porsche. Energy: The transformation should feel high-energy and "force-driven," while the final gesture is soft and charismatic.$