underwood's banner

underwood

@underwoodxie96 • 39,621 subscribers

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

Shorts

Dark Magician Girl, activate! The last cosplay transformation video I posted on Instagram has already passed 300K views. Honestly, I didn’t expect that.

Dark Magician Girl, activate! The last cosplay transformation video I posted on Instagram has already passed 300K views. Honestly, I didn’t expect that.

585,066 views

I made a new Sailor Moon live-action transformation video. Hope you like it! Which character should I make next? Tell me in the comments. The full workflow, prompt, and Canvas share link are in the comments.

I made a new Sailor Moon live-action transformation video. Hope you like it! Which character should I make next? Tell me in the comments. The full workflow, prompt, and Canvas share link are in the comments.

592,381 views

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.

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.

312,445 views

After two rounds of practice, this one went much faster. A lot of video effects that look complicated become much easier once you break them down into smaller modules. Here are 3 small tips I’ve learned for making this kind of video: 1. Show the final result at the beginning to set expectations 2. Let the decorative elements stay on screen for 2 extra seconds at the start of each segment 3. Cut out the clips where the AI motion goes wrong Full workflow and prompts:

After two rounds of practice, this one went much faster. A lot of video effects that look complicated become much easier once you break them down into smaller modules. Here are 3 small tips I’ve learned for making this kind of video: 1. Show the final result at the beginning to set expectations 2. Let the decorative elements stay on screen for 2 extra seconds at the start of each segment 3. Cut out the clips where the AI motion goes wrong Full workflow and prompts:

207,003 views

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

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

622,294 views

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:

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:

178,219 views

We launched 7 new AI video effects this week ✨ No prompts needed—just upload a photo and turn it into a fun video in a few clicks. They work with people, pets, and a wide range of image styles. Here are two of the latest effects. Give them a try 👇 🔗

We launched 7 new AI video effects this week ✨ No prompts needed—just upload a photo and turn it into a fun video in a few clicks. They work with people, pets, and a wide range of image styles. Here are two of the latest effects. Give them a try 👇 🔗

15,535 views

Seedance 2.0 Mini is now available on our platform, starting at just $0.07 per second. The effect is pretty good! Upload your image here to create your own version:

Seedance 2.0 Mini is now available on our platform, starting at just $0.07 per second. The effect is pretty good! Upload your image here to create your own version:

47,003 views

I think you'll like this dance.

I think you'll like this dance.

415,373 views

Tried a few rounds and finally found a more stable prompting trick: 1. Clearly describe the character order and positioning in the prompt, such as “from left to right” or “foreground to background,” which can noticeably reduce the failure rate. 2. Add “no red lines, no annotation lines, no guide lines” to the negative prompt to reduce red line artifacts and first-frame errors. This time, I’m using this method to create a “World Cup cheer squad backstage” scene. Prompt in the comments.

Tried a few rounds and finally found a more stable prompting trick: 1. Clearly describe the character order and positioning in the prompt, such as “from left to right” or “foreground to background,” which can noticeably reduce the failure rate. 2. Add “no red lines, no annotation lines, no guide lines” to the negative prompt to reduce red line artifacts and first-frame errors. This time, I’m using this method to create a “World Cup cheer squad backstage” scene. Prompt in the comments.

76,919 views

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.

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.

304,568 views

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

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

95,813 views

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. 🚀

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. 🚀

50,649 views

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.

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.

55,928 views

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.

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 views

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

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

47,455 views

Thanks to 𝗦𝗮𝗻𝗶𝗮 for sharing the prompts, I've created a Maldives-themed travel video! It's incredibly authentic! prompt： Preserve the exact face, hairstyle, identity, skin tone, and body proportions from [image1] throughout the entire video. Outfit: bikini swimsuit, brown leather sandals, small gold hoop earrings. Loose natural wavy hair. A real Indonesian woman on vacation in the Maldives. Late-2000s personal video blog aesthetic. Extremely rough handheld flip-camera footage, with heavy camera shake, natural reframing, partial face cropping, focus hunting, exposure shifts, warm faded colors, slight digital noise, and home-video imperfections. No posing, no cinematic glamour, no stabilization, no modern color grading. 00:00–00:02 Small speedboat deck. Selfie shot, strong sea breeze, she smiles and casually talks. Behind her: turquoise lagoon, white boat wake, and distant overwater villas. 00:02–00:04 Sandy island road. She walks while filming herself, passing bicycles, palm trees, and low guesthouses. The camera bounces with her footsteps. 00:04–00:06 Local small cafe. She sits on a plastic chair holding an iced drink, briefly chats with the owner, then laughs. The camera goes out of focus for a moment before finding her face again. 00:06–00:08 Shallow white-sand beach. She crouches and touches the clear seawater with one hand. Small waves reach near her sandals, and bright sunlight makes the exposure flicker. 00:08–00:10 End of a wooden jetty. She checks a small map/notebook and looks curiously toward a docked dhoni boat and the pale green sea beyond it. 00:10–00:12 Edge of a sandbank. She walks into the wind, shading her eyes with one hand as she looks toward the horizon. Her hair gets messy, and the camera occasionally cuts off half her face. 00:12–00:15 Sunset jetty. Selfie shot. She smiles, waves, casually says something, then the camera suddenly tilts toward the sky and sea as the recording naturally cuts off. Natural location sound only: speedboat engine, waves, distant boats, seabirds, cafe chatter, footsteps in sand, wind, and rustling palm leaves. no music, no subtitles

Thanks to 𝗦𝗮𝗻𝗶𝗮 for sharing the prompts, I've created a Maldives-themed travel video! It's incredibly authentic! prompt： Preserve the exact face, hairstyle, identity, skin tone, and body proportions from [image1] throughout the entire video. Outfit: bikini swimsuit, brown leather sandals, small gold hoop earrings. Loose natural wavy hair. A real Indonesian woman on vacation in the Maldives. Late-2000s personal video blog aesthetic. Extremely rough handheld flip-camera footage, with heavy camera shake, natural reframing, partial face cropping, focus hunting, exposure shifts, warm faded colors, slight digital noise, and home-video imperfections. No posing, no cinematic glamour, no stabilization, no modern color grading. 00:00–00:02 Small speedboat deck. Selfie shot, strong sea breeze, she smiles and casually talks. Behind her: turquoise lagoon, white boat wake, and distant overwater villas. 00:02–00:04 Sandy island road. She walks while filming herself, passing bicycles, palm trees, and low guesthouses. The camera bounces with her footsteps. 00:04–00:06 Local small cafe. She sits on a plastic chair holding an iced drink, briefly chats with the owner, then laughs. The camera goes out of focus for a moment before finding her face again. 00:06–00:08 Shallow white-sand beach. She crouches and touches the clear seawater with one hand. Small waves reach near her sandals, and bright sunlight makes the exposure flicker. 00:08–00:10 End of a wooden jetty. She checks a small map/notebook and looks curiously toward a docked dhoni boat and the pale green sea beyond it. 00:10–00:12 Edge of a sandbank. She walks into the wind, shading her eyes with one hand as she looks toward the horizon. Her hair gets messy, and the camera occasionally cuts off half her face. 00:12–00:15 Sunset jetty. Selfie shot. She smiles, waves, casually says something, then the camera suddenly tilts toward the sky and sea as the recording naturally cuts off. Natural location sound only: speedboat engine, waves, distant boats, seabirds, cafe chatter, footsteps in sand, wind, and rustling palm leaves. no music, no subtitles

17,255 views

seedance 2.0 Crazy McDonalds

seedance 2.0 Crazy McDonalds

83,351 views

Today I saw a user share a really interesting prompt on the website. I made a similar version inspired by it, and the result was hilarious 😂 You’re welcome to explore more AI image and video prompts on Promptsref. We’ve already collected over 10,000 high-quality prompts and use AI algorithms to connect similar styles, characters, scenes, and use cases, so you can find inspiration much faster. Video prompt: Original version from the website user:

Today I saw a user share a really interesting prompt on the website. I made a similar version inspired by it, and the result was hilarious 😂 You’re welcome to explore more AI image and video prompts on Promptsref. We’ve already collected over 10,000 high-quality prompts and use AI algorithms to connect similar styles, characters, scenes, and use cases, so you can find inspiration much faster. Video prompt: Original version from the website user:

11,441 views

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.

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.

32,281 views

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

I used AI to create this transformation video, and I'm pretty happy with how it turned out. The entire workflow required 11 keyframe images and 7 short video clips. The hardest part was the clothing transition. Current AI models still leave noticeable artifacts during the dressing process, so I had to trim and hide many of those frames in editing. After several iterations, this version finally feels smooth and believable. Full workflow + prompts:

I used AI to create this transformation video, and I'm pretty happy with how it turned out. The entire workflow required 11 keyframe images and 7 short video clips. The hardest part was the clothing transition. Current AI models still leave noticeable artifacts during the dressing process, so I had to trim and hide many of those frames in editing. After several iterations, this version finally feels smooth and believable. Full workflow + prompts:

102,104 views • 1 month ago

This is insane! What AI model made this?🤪

This is insane! What AI model made this?🤪

109,984 views • 6 months ago

I've made some new videos, I hope you like them. Complete prompts and tutorials:

I've made some new videos, I hope you like them. Complete prompts and tutorials:

20,390 views • 1 month ago

Using Nano Banana Pro + Sora, I can now create a short video in just about one minute. I’ve been using Kling for a while to make short videos, and while the results can be great, the workflow has always felt a bit heavy for me. Previously, I had to export the video frame by frame as images, then send those keyframes into Kling’s first/last frame mode to generate the in-betweens. It worked, but it took a lot of time and small steps. Recently I realized I don’t necessarily need to do that anymore: now I can use Nano Banana Pro to generate the images, then send them directly to Sora to create the short video—no need to manually extract a specific frame. Another bonus is that Sora also handles basic sound design for you, which saves me from an extra round of editing and makes the whole process feel much lighter. This idea actually came from a post I saw this morning on Twitter by SD | AI Animation Storyteller, which gave me a new way of thinking about my workflow. I’m still experimenting, but so far it’s been a big improvement in efficiency for my use case. I’ve put the detailed steps I’m using in the comments in case anyone wants to try something similar.

Using Nano Banana Pro + Sora, I can now create a short video in just about one minute. I’ve been using Kling for a while to make short videos, and while the results can be great, the workflow has always felt a bit heavy for me. Previously, I had to export the video frame by frame as images, then send those keyframes into Kling’s first/last frame mode to generate the in-betweens. It worked, but it took a lot of time and small steps. Recently I realized I don’t necessarily need to do that anymore: now I can use Nano Banana Pro to generate the images, then send them directly to Sora to create the short video—no need to manually extract a specific frame. Another bonus is that Sora also handles basic sound design for you, which saves me from an extra round of editing and makes the whole process feel much lighter. This idea actually came from a post I saw this morning on Twitter by SD | AI Animation Storyteller, which gave me a new way of thinking about my workflow. I’m still experimenting, but so far it’s been a big improvement in efficiency for my use case. I’ve put the detailed steps I’m using in the comments in case anyone wants to try something similar.

46,400 views • 7 months ago

Our website now supports Kling Motion Control. Today, creating an AI influencer video has become incredibly simple. You can first use Nano Banana Pro to generate realistic images, then use Kling Motion Control to replace the motion and quickly create viral-style videos for social media. We also provide a selection of popular online dance motions with controllable presets for you to use. If you're interested, feel free to try it on our website:

Our website now supports Kling Motion Control. Today, creating an AI influencer video has become incredibly simple. You can first use Nano Banana Pro to generate realistic images, then use Kling Motion Control to replace the motion and quickly create viral-style videos for social media. We also provide a selection of popular online dance motions with controllable presets for you to use. If you're interested, feel free to try it on our website:

15,467 views • 4 months ago

I ran a quick test: I used the exact same prompt to generate videos with Seedance 2.0 and Sora 2, just to see how they differ. Sora 2 automatically adds music, which instantly makes the video feel polished. But Seedance 2.0 handles shot breakdown and pacing better, it feels more like a professionally edited sequence.

I ran a quick test: I used the exact same prompt to generate videos with Seedance 2.0 and Sora 2, just to see how they differ. Sora 2 automatically adds music, which instantly makes the video feel polished. But Seedance 2.0 handles shot breakdown and pacing better, it feels more like a professionally edited sequence.

13,972 views • 5 months ago

No more content to load