[00:02] actually looks good. I've been testing it for the past week and I've been able to create full anime scenes in less than 15 minutes. Just take a look at this.
[00:45] it and start creating your own anime scenes today, even if you've never touched an AI tool before. Now, there are two popular methods you can use with any AI video generator, text-to-video and image-to-video. The first one is as
[00:58] simple as it sounds. You write a prompt and get a video back. However, image-to-video takes an image as input and builds an entire video on top of it. Now, SeaDance 2.0 supports both of them and with text-to-video, you can get
[01:10] want results like the ones you just saw in the intro, you need to use for that comes down to three things. First, it saves you a lot of wasted describe your character in the prompt,
[01:24] right, you adjust the description and regenerate. Then you repeat over and your credits trying to get it right. Instead, you can build one good image with all the details you want up front and then generate the perfect video on
[01:38] top of it from the first try. Second, it keeps every detail consistent across all because SeaDance is always looking at the same reference images right before to worry about weird changes between clips anymore. And third, it gives you
[01:53] generate. If something about your character or location doesn't look right, you can simply edit the reference image first and the final video will match exactly that. So, this is exactly why we always want to use references for
[02:06] our anime generation. But before we can actually use them, we first need to build them. For this, I found one simple method that does wonders every time. So, let me show you the only two steps you actually need to make this work. First,
[02:18] you want to describe your character or location in plain natural language, friend. This is where you include all the details you want the AI to add to the environment feels like, or anything else that matters for the final result.
[02:32] making it sound like a polished AI prompt. Just write it the way it comes to you. This is exactly what I wrote for my character. Now, once you have that take it into Claude and ask it to rewrite everything into a proper prompt
[02:46] for the exact model you're using. And in our case, that's going to be NanoBanana best image models. Claude is really good for this task because it understands how these models work and how to structure the prompt to get the best possible
[02:59] back for my character. Now, let's actually test it inside NanoBanana Pro. because it gives me access to all the models we need for this workflow, including SeaDance 2.0. So, if you want to follow the same process, I'll leave a
[03:13] link in the description below. Once you're inside, go to the image section and click on create image. From here, select NanoBanana Pro as the model and Then just click generate and wait and
[03:25] there's nothing I can really complain about. The character has all the details I asked for and it genuinely looks like anime. The Ghibli style feels spot on and it even has that soft hand-painted look. Because this is the image SeaDance
[03:38] time, it's worth getting it exactly how you want before moving on. Now, let's do the exact same thing for the locations. The first one is going to be a mountain lake at dawn. So, again, I'll write out all the details I want in normal
[03:51] it turn everything into a polished prompt. Once I have that, I go back to Higgsfield, select Nano Banana Pro, and generate the image. Look at this. It looks beautiful. The transparency of the water came out so well that you can
[04:04] really like how this turned out, so now location for our anime. This one is going to be a lakeside cabin. And again, And here's the image we get back. It looks warm and cozy, which is exactly
[04:18] And with that, we now have all three reference images ready. However, if you don't pay close attention to the next step, you can very easily waste all the work we've done so far. And that's because the reference images alone won't
[04:31] get you amazing results. To get those, you need to know how to properly write prompts inside C Dance. And because this model is quite different from any AI my personal prompting framework. It's called McCall, and it's fully customized
[04:44] for the new C Dance 2.0. So, if you want to follow along with the tutorial and Higgsfield in the description below. All right. So, the McCall framework is made up of five different elements. The M stands for multi-shot, and this is
[04:58] easily the most important one. That's because C Dance 2.0 only takes a single describe the whole scene like one continuous flow, the model has no idea where one shot ends and the next one begins. And what you get back feels more
[05:11] like an anime screensaver than a real sequence. Think about it. Any real anime scene you've ever seen, even a slow one, is never just one continuous shot. It's always a sequence of moments pieced together. So, instead, you want to break
[05:23] those 15 seconds into three to six separate shots inside the prompt. Each shot becomes its own beat, almost like a storyboard the model can follow frame by boy waking up on the lake. So, I'll split that into three shots. An aerial
[05:37] view of the lake, a close-up beside the boat as he stirs, and a medium shot as he sits up and smiles. So, the prompt for our first scene will look like this. Now, inside every shot, you also need to say exactly what the character is doing.
[05:49] mess it up. They describe the setting in perfect detail, but barely mention what's actually happening in the frame. So, C-Dance either keeps the character random, and you don't want either of those. That's why the A in McCall stands
[06:03] for action. For shot two, that's the boy lying asleep inside the boat. Then he slowly stirs, opens his eyes, and squints into the soft morning light. Every verb there is a cue for the model, and the more specific you are, the less
[06:15] look at this line in shot one. Camera sunbeams sparkling on the water. This is exactly the scene from our framework. It's the camera movement, and this is what makes good-looking anime actually
[06:27] become cinematic. So, for our first shot, I want that aerial view slowly descending toward the rowboat. For the second, a low-angle close-up beside the boat. And for the third, a medium shot that holds on the character as he sits
[06:39] across 15 seconds, and that alone already makes the entire sequence feel more dynamic. But now we get to one of the most underused parts of the entire framework, audio. You see, even some so-called experts complicate this a lot
[06:53] with sound overs. But C-Dance 2.0 can actually generate audio directly inside the clip. That's what the second A stands for, audio. And for anime, sound you don't believe me, try to watch an anime on mute, and you'll quickly
[07:06] realize it's not the same anymore. So, at the bottom of our prompt, I'll add a separate audio section and list exactly what I want to hear. For our first distant bird calls, and a few more. The key is to tie the sound to specific
[07:19] moments in the shot, not just describe vague background noise. Now, the last letter in the framework is L, which stands for lighting. Ghibli-style scenes that's where so much of the mood comes from. But when you describe it properly,
[07:32] the model locks into that exact palette and holds it across every frame. So, for our opening shot, I'm going to layer it in clear with a golden dawn sky and you want to get the best results, you want to add this lighting note to every
[07:45] part that makes the whole framework click. When you stack all five letters together, you end up with a prompt that tells SeaArt exactly how to stage the character, paint the frame, and score the sound. Once you put together all
[07:59] five elements of the Mac all framework, you'll get a prompt that looks like inside the video sections and select the SeaArt 2.0 model. Next, I'll click on upload media to add the reference images I've created previously. But, before you
[08:13] do that, make sure your reference is eligible. This is a safety feature from the wrong kind of content. So, let's upload the character image and the duration to 15 seconds, paste in the prompt, and hit generate.
[08:44] than I expected. The camera movement flows naturally from the aerial view lighting stays consistent through the entire sequence. But, what impressed me water lapping in perfect sync with the movement, and it adds so much to the
[08:58] realism. So, with the Mac all framework, you can now create a high-quality scene generated the first scene. There are a couple more to go, and then it will come to the most important part of the entire video. So, let's first create the
[09:11] remaining scenes. The second scene is where the boy catches a fish with a net. the exact same process we just went through because SeaArt works the same way for every scene. The only thing that changes is the content of the prompt
[09:23] letter of Mac all and build out the shots, the action, the camera movement, the audio, and the lighting. And here's the full prompt I came up with for this one. The reference images stay the same, the boy and the mountain lake, because
[09:36] this scene still takes place on the water. So, I'll paste the prompt in, set the duration to 15 seconds, and hit generate.
[09:54] solid, and what I like best is his expression when he caught the fish. But, now let's get to the third scene. This is where the boy rows back to shore and one key change from before. Because this scene now includes the cabin, I'll also
[10:07] add the second location image as reference. So, we go from two reference all of them to keep everything consistent with what we've already process. Write out the McCall prompt, paste it in, and hit generate. Here's
[10:21] the prompt for this scene. And here's what we get back.
[10:40] generated. The motion feels completely natural, and the Ghibli style still holds up beautifully across every shot. And the last scene is the grilling the fire. For this one, there's another small change. Since the action now
[10:54] happens back at the cabin, and the lake isn't in frame anymore, I'll remove the first location image from the reference list, so the final setup uses just the boy and the cabin references. And here's the prompt I built for this scene. Same
[11:06] process again, set the duration, paste in the prompt, and hit generate. Take a in the prompt, and hit generate. Take a look at it.
[11:27] now, they're four separate clips. We need to somehow to all of them together into one single video. But, this step is quite simple compared to what we've done so far. Let's jump inside CapCut and drag all four scenes straight onto the
[11:39] trim anything that you don't like or add quick transitions between the clips. flows pretty well. So, I'll just hit export. Now, let's see the final result.
[12:24] the most impressive AI anime videos I've seen in the last period. The style holds natural, and it actually looks like a Studio Ghibli short. But, all of that is thanks to the new SeaArt 2.0. So, if you want to start creating your own AI
[12:38] link in the description and get full access to SeaArt, Nano Banana Pro, and Thanks for watching, and see you in the next one.