正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

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. 🚀

underwood

39,003 subscribers

49,969 次观看 • 29 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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.

underwood

311,522 次观看 • 27 天前

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:

underwood

176,477 次观看 • 1 个月前

~70% of Waymo’s top engineers are Chinese. The harder robotaxi solutions are being solved by Pony, Apollo, WeRide, etc. The more ambitious engineers are coming back to China for a real challenge. This situation is a regular example of how much more challenging driving logic is in China

~70% of Waymo’s top engineers are Chinese. The harder robotaxi solutions are being solved by Pony, Apollo, WeRide, etc. The more ambitious engineers are coming back to China for a real challenge. This situation is a regular example of how much more challenging driving logic is in China

Taylor Ogan

74,411 次观看 • 7 个月前

GPT Image 2 + Seedance 2.0 Prompt Share Created on mitte.ai I didn't use a character sheet for this generation. I directly used the character images I created in Midjourney. Since the visual style transfers into the video surprisingly well, it's actually a really effective for style transfer. This time I also added a bit more detail to the Seedance prompt itself. You can definitely achieve similar results without storyboards too, they're not mandatory but I think they're one of the best ways to previsualize scenes, pacing and even camera angles before generation. Also, this storyboard prompt is still a bit long. I'm currently experimenting with more compact version of it too. You can check the prompts below.

GPT Image 2 + Seedance 2.0 Prompt Share Created on mitte.ai I didn't use a character sheet for this generation. I directly used the character images I created in Midjourney. Since the visual style transfers into the video surprisingly well, it's actually a really effective for style transfer. This time I also added a bit more detail to the Seedance prompt itself. You can definitely achieve similar results without storyboards too, they're not mandatory but I think they're one of the best ways to previsualize scenes, pacing and even camera angles before generation. Also, this storyboard prompt is still a bit long. I'm currently experimenting with more compact version of it too. You can check the prompts below.

Kōda

38,856 次观看 • 1 个月前

What makes Willow special is how it handles qubits. Qubits are powerful, but incredibly fragile. The more you increase them, the more likely they are to produce errors in computations.

What makes Willow special is how it handles qubits. Qubits are powerful, but incredibly fragile. The more you increase them, the more likely they are to produce errors in computations.

Kevin Joey Chen

414,965 次观看 • 1 年前

Today is United Nations Day – and also the United Nations's 80th anniversary! The UN is the world's most universal international organization, making it truly global in reach, but it's also much more: it's a "living promise that spans borders, bridges continents, and inspires generations."

Today is United Nations Day – and also the United Nations's 80th anniversary! The UN is the world's most universal international organization, making it truly global in reach, but it's also much more: it's a "living promise that spans borders, bridges continents, and inspires generations."

UNTMIS

28,309 次观看 • 8 个月前

🚨How to Easily Create a Hyper-Realistic Clone of Yourself in a few clicks 🚀 I’ll show you the complete workflow here to create your clone with ease. (Bookmark and get ready to be blown away) 🧵🔽

🚨How to Easily Create a Hyper-Realistic Clone of Yourself in a few clicks 🚀 I’ll show you the complete workflow here to create your clone with ease. (Bookmark and get ready to be blown away) 🧵🔽

Pierrick Chevallier | IA

177,247 次观看 • 1 年前

Anna's started her defence apprenticeship and is looking forward to what's ahead. The Defence Industrial Strategy will create thousands more opportunities like this, supporting the next generation 🚀

Anna's started her defence apprenticeship and is looking forward to what's ahead. The Defence Industrial Strategy will create thousands more opportunities like this, supporting the next generation 🚀

Ministry of Defence 🇬🇧

18,239 次观看 • 9 个月前

"Preparation to win is much more important than the will to win. But, if you combine the preparation to win and the will to win...you have a chance." Everybody wants to win. Few prepare for it.

"Preparation to win is much more important than the will to win. But, if you combine the preparation to win and the will to win...you have a chance." Everybody wants to win. Few prepare for it.

The Winning Difference

14,477 次观看 • 3 个月前

Took this an hour and a half before @kamalaharris was scheduled to show here in deep-blue Madison. People are packed to the rafters. Campaign says more than 10,500, which is as many as the fire marshal allowed.

Took this an hour and a half before @kamalaharris was scheduled to show here in deep-blue Madison. People are packed to the rafters. Campaign says more than 10,500, which is as many as the fire marshal allowed.

Karen Tumulty

1,159,118 次观看 • 1 年前

Most people focus on better prompts, but the real breakthrough is having a repeatable creative workflow. Building a consistent character first, then turning it into storyboards and videos makes AI anime production far more reliable. Every serious AI influencer creator should be thinking beyond one-shot generations.

Most people focus on better prompts, but the real breakthrough is having a repeatable creative workflow. Building a consistent character first, then turning it into storyboards and videos makes AI anime production far more reliable. Every serious AI influencer creator should be thinking beyond one-shot generations.

FATHELA ESQ

22,384 次观看 • 1 天前

Even when the Red Sox are given a gift, this is the result. I don’t hate this send as much as the one a few days back. Definition of a perfect throw.

Even when the Red Sox are given a gift, this is the result. I don’t hate this send as much as the one a few days back. Definition of a perfect throw.

Tyler Milliken

99,897 次观看 • 1 个月前

Hello interns! Here is a little recording of our game! We are finishing a few details before having the first version for the beta testers! What are you waiting for! Join our corporation! (More info in our bio!) #sizetwitter #giantess #巨大娘

Hello interns! Here is a little recording of our game! We are finishing a few details before having the first version for the beta testers! What are you waiting for! Join our corporation! (More info in our bio!) #sizetwitter #giantess #巨大娘

GtsCorp

43,846 次观看 • 2 年前

The Taking of the Relic Made with GPT Image 2 + Seedance 2 on mitte.ai This time I started with a storyboard, then moved to video. The main reason is cost. Video iterations burn credits really fast. With a storyboard, I can tweak things shot by shot and catch issues early, which is way cheaper. It also makes the whole process more controllable. I can adjust each shot on its own, so the character, composition, and key elements stay consistent. Pacing gets figured out early. Once the storyboard is done, the flow is pretty much set. The video step is just turning those shots into a sequence. Sharing my workflow 👇

The Taking of the Relic Made with GPT Image 2 + Seedance 2 on mitte.ai This time I started with a storyboard, then moved to video. The main reason is cost. Video iterations burn credits really fast. With a storyboard, I can tweak things shot by shot and catch issues early, which is way cheaper. It also makes the whole process more controllable. I can adjust each shot on its own, so the character, composition, and key elements stay consistent. Pacing gets figured out early. Once the storyboard is done, the flow is pretty much set. The video step is just turning those shots into a sequence. Sharing my workflow 👇

Latte

17,469 次观看 • 2 个月前

i found the video version and it genuinely makes this so much more funnier holy shit

i found the video version and it genuinely makes this so much more funnier holy shit

Sarah / Fortnite leaks & news🗞️

1,347,732 次观看 • 10 个月前

Testing with a more challenging footage. Here I applied Da vinci Magic Mask to avoid it detecting much more people than it should. Thanks Massi Nissa for the suggestion and the idea for the footage💪 Talking with him, gave some ideas to make it easier to run the process.

Testing with a more challenging footage. Here I applied Da vinci Magic Mask to avoid it detecting much more people than it should. Thanks Massi Nissa for the suggestion and the idea for the footage💪 Talking with him, gave some ideas to make it easier to run the process.

Carlos Barreto

18,834 次观看 • 2 个月前

Jerry Seinfeld to Jimmy Fallon while on The Tonight Show... "What you want in a pancake is to have the consistency of young human flesh" This is much more than a sick "inside" joke... It is how these kinda people operate as The Epstein files show...

Jerry Seinfeld to Jimmy Fallon while on The Tonight Show... "What you want in a pancake is to have the consistency of young human flesh" This is much more than a sick "inside" joke... It is how these kinda people operate as The Epstein files show...

Isaac’s Army

122,797 次观看 • 4 个月前

🇮🇷Many on X are reporting that Iran's 2 largest cities "have fallen" to protesters They are referring to Tehran and Mashhad While this cannot be verified, I definitely don't expect the cities to be "under the control" of protesters, as that would be the end of the regime. What I assume is happening is law enforcement retreating, likely to their headquarters. But it is unlikely the cities have fallen. A heavy-anded crackdown is coming. Expect violence. But also don't expect the regime to last much longer based on how things are looking.

🇮🇷Many on X are reporting that Iran's 2 largest cities "have fallen" to protesters They are referring to Tehran and Mashhad While this cannot be verified, I definitely don't expect the cities to be "under the control" of protesters, as that would be the end of the regime. What I assume is happening is law enforcement retreating, likely to their headquarters. But it is unlikely the cities have fallen. A heavy-anded crackdown is coming. Expect violence. But also don't expect the regime to last much longer based on how things are looking.

Mario Nawfal

17,543 次观看 • 5 个月前

This is a beautiful moment of two sockeye salmons spawning. What makes it more special is that it's the first time in years salmon has returned to this creek to spawn. These two are the comeback of a new era.

This is a beautiful moment of two sockeye salmons spawning. What makes it more special is that it's the first time in years salmon has returned to this creek to spawn. These two are the comeback of a new era.

Kirk Lubimov

19,619 次观看 • 9 个月前

This workflow is perfect for creating short fashion-style cinematic videos. I simplified the original prompts based on willie’s method, and the whole process is now much faster and more stable: 1. Generate a 3×3 keyframe grid (Nano Banana Pro only) Use this simple prompt: “In a 3x3 grid, show this character in different angles, keep the scene the same, random poses. This is far simpler and more efficient than my old prompts. You can generate multiple times and just pick the keyframes you like most. 2. Extract a high-res keyframe (Super stable trick) Take a screenshot of the keyframe you want from the 3×3 grid, send it back to Nano Banana Pro, and simply say: “Give me a high-resolution version.” This method is much more stable than relying on complex upscaling prompts. 3. Generate the video with Kling 2.5 Turbo Upload the first and last frames to Kling 2.5 Turbo and use this prompt: “The camera very slowly and smoothly lowers on a boom.” From my testing, Kling 2.5 Turbo offers the best balance of stability and cost — other models are either less consistent or noticeably more expensive. 4. Final speed adjustment with willie’s tool (Critical step) Use the tool built by willie to fine-tune the playback speed of each clip. This step is essential for getting that premium cinematic feel. I’ll drop the tool link in the comments.

This workflow is perfect for creating short fashion-style cinematic videos. I simplified the original prompts based on willie’s method, and the whole process is now much faster and more stable: 1. Generate a 3×3 keyframe grid (Nano Banana Pro only) Use this simple prompt: “In a 3x3 grid, show this character in different angles, keep the scene the same, random poses. This is far simpler and more efficient than my old prompts. You can generate multiple times and just pick the keyframes you like most. 2. Extract a high-res keyframe (Super stable trick) Take a screenshot of the keyframe you want from the 3×3 grid, send it back to Nano Banana Pro, and simply say: “Give me a high-resolution version.” This method is much more stable than relying on complex upscaling prompts. 3. Generate the video with Kling 2.5 Turbo Upload the first and last frames to Kling 2.5 Turbo and use this prompt: “The camera very slowly and smoothly lowers on a boom.” From my testing, Kling 2.5 Turbo offers the best balance of stability and cost — other models are either less consistent or noticeably more expensive. 4. Final speed adjustment with willie’s tool (Critical step) Use the tool built by willie to fine-tune the playback speed of each clip. This step is essential for getting that premium cinematic feel. I’ll drop the tool link in the comments.

underwood

21,996 次观看 • 6 个月前