Brief Summary
This tutorial provides a step-by-step guide on creating animations in the style of Pixar and Disney using AI tools. It covers writing a story with customizable templates, generating images with Leonardo AI, converting images to videos with Kling AI, using 11 Labs AI for voice narration, and editing the final video in Adobe Premiere Pro. The process enables users to produce high-quality animations without needing extensive technical skills or expensive software.
- Writing impactful story using customizable template.
- Generating images with Leonardo AI and maintaining character consistency.
- Converting images into videos using Kling AI.
- Adding AI-generated voice narration using 11 Labs AI.
- Editing and combining all elements in Adobe Premiere Pro.
The video introduces a tutorial on creating animations in the style of Pixar and Disney using AI tools. It highlights that creating such animations no longer requires expensive hardware or expertise in complex software like 3ds Max, Maya, Cinema 4D, or Blender. AI-powered image and video generators allow users to create incredible videos and animations without technical skills, supporting various animation styles like 2D, 3D, photorealistic, cartoon, anime, and comic styles. The tutorial will guide viewers on crafting effective text prompts for characters, actions, backgrounds, and animation styles, utilizing AI tools like Leonardo, Kling, and 11 Labs to transform ideas into stunning images, videos, and animations.
The initial step in creating an animation involves writing a compelling story. A customizable template is provided, which includes all necessary elements for story creation. This template can be found in the video description on the Iman Global YouTube channel. Users can copy and customize the template based on their preferences and use AI tools like Chat GPT, Gemini, or Claude to generate a story based on the template's rules. The template is divided into two sections: the first section requires defining the story's theme and the appearance of the main character, specifying details like age, clothes, hairstyle, and shoes. This ensures consistency in image generation, as AI tools process each prompt separately, and consistent character details are necessary for maintaining uniformity across images. The second section prompts Chat GPT to provide a story based on the inputs, including prompts for image creation and narration text.
After creating the story, the next step involves using an image-generating AI, such as Leonardo AI, to create the visuals. Leonardo AI is chosen for its sufficient free credits and high-quality image generation capabilities. Users visit the Leonardo AI website, create a free account, and log in. In the Leonardo dashboard, they select the image creation option and paste the first image prompt copied from Chat GPT into the prompt box. The Phoenix 1.0 model is selected from the preset dropdown, prompt enhance is turned off, and the Dynamic preset style is chosen. The generation mode is set to fast, and the image dimensions are set to a 16:9 ratio for a horizontal long format suitable for YouTube. After adjusting the settings, the images are generated, and users can review and download the ones they like.
To maintain character consistency across different scenes, users can copy the seed number from a generated image by clicking the three-dot icon and selecting "copy seed". This seed number is then pasted into the "use fixed seed" option in the advanced settings of Leonardo AI. This ensures that the character's form remains consistent in subsequent images. The process of copying image prompts from Chat GPT, pasting them into Leonardo AI, and generating images is repeated for each scene, ensuring that the characters remain almost identical with different backgrounds and scenarios. Leonardo AI provides 150 free tokens daily, which are replenished the next day, and paid plans are available for those needing more tokens.
The images generated by Leonardo AI are converted into videos and animations using Kling AI. Users visit the Kling AI website and either try the trial package or sign up for an account. After logging in, they access the AI videos section and select the "image to video" tab. Here, they can upload images in JPG and PNG formats, with a maximum size of 10 MB and minimum dimensions of 300 pixels. After uploading an image, users can type ideas for animating the image in the prompt section. The standard mode is used for faster generation speed in the free plan, and the video length can be set between 5 and 10 seconds. After adjusting the settings, users click the generate button, which deducts 10 tokens from their credit. The generated video can be downloaded for free, but videos in the free account have watermarks.
After creating the story and converting the images into videos, the story needs to be narrated. Users can record the narration themselves or use AI-generated voices from 11 Labs AI. They visit the 11 Labs AI website, create a free account, and log in. They then copy the voiceover sections from Chat GPT and paste them into the text-to-speech section of 11 Labs AI. Users can choose a narrator's voice from the dropdown list and click the generate speech button. The narrator's audio file can then be downloaded.
The final step involves editing and combining the story animations and narrator's voice in a video editing software like Adobe Premiere Pro. Users create a new project, name it, and specify a save location. They import the animations and audio files into the project panel. A new sequence is created, defining the sequence dimensions and assigning a name. The videos are dragged and dropped onto the timeline, and the "scale to frame size" option is used to ensure the video dimensions match the sequence dimensions. The short videos are arranged sequentially on the timeline, and the narrator's audio file is added to synchronize the video with the narrator's voice. The razor tool is used to split the audio track and place the narrator's voice at the correct points. Finally, the video is exported in h264 format with full HD output size and dimensions.
Summarize any YouTube video in seconds
Get summaries like this one for any video, in your language, with the free Summ app.
Transcript
Full transcript of “AI Video Generator: Convert Text into 3D Animated Stories | AI Animation Maker | Text-to-Video AI”. Click a timestamp to open the video at that moment. Need another video? Use the YouTube transcript generator.
0:00 do you dream of creating breathtaking animations in the iconic 2D and 3D styles of Pixar and Disney do you want to turn your ideas into real stories if your answer is yes welcome to this tutorial here you'll discover revolutionary AI tools that transform your simple text into stunning animated videos nowadays creating animations akin to Pixar and Disney doesn't require expensive Hardware or expertise in complex software like 3ds Max Maya Cinema 4D blender and more with today's AI powered image and video generators you can create incredible videos and animations without technical skills in minimal time and at no cost these AI tools support a wide range of Animation Styles including 2D 3D photorealistic
0:46 cartoon anime and comic Styles this means you can bring your most creative ideas to life whether it's a promotional video a game trailer a short animation or anything else you can imagine you don't even need storytelling or screenplay expertise with the help of chat GPT and AI you can get started right away in this tutorial I'll show you how to craft effective text prompts to describe characters actions backgrounds and animation Styles pioneering AIS like Leonardo cing pix verse and Minimax have revolutionized image and video production so let's explore how they work I'll guide you stepbystep to use AI for turning your ideas into stunning images videos and animations
1:32 hi everyone my name is Ean and this is the Ean Global YouTube channel welcome back to another AI tutorial please support my YouTube channel don't forget to like And subscribe let's get started the first step in creating an animation is writing a good and impactful story for this purpose I have written a template with customizable parameters that includes everything you need to create a story you can find this template in the description of my video on my channel and M Global simply copy it customize it based on your preferences and needs and give it to AI tools like chat GPT gemini or claw to generate a story for you based on the
2:18 templates rules I have divided this text template into two sections in the first section which is editable you need to define the story's theme and the appearance of the main character based on your idea for instance if the main character of your story is a playful and mischievous girl you should specify her features such as age clothes hairstyle shoes and other details to create a text prompt for generating an image why is this necessary because image generating AIS process each prompt separately and if the details of the main character are not consistently repeated in every prompt the images May differ in each generation however using this organization the prompts will have similar character description i s ensuring consistency of the story's character across all scenes in the
3:04 second section of this guide we ask chat GPT to provide a story based on our inputs including prompts for image creation and narration text I have already defined the character's appearance in this prompt now I simply copy and paste this prompt into chat GPT and as you can see chat GPT creates the entire story based on our requirements prompts for image creation and narration text I copy the first prompt to create the first image next we use an image generating AI such as piman design mid Journey or others my choice is Leonardo because it provides sufficient credits in its free plan to create images and is one of the best image generators in the world we visit the Leonardo AI image generator website create a free account and log in
3:51 from the left menu click on the image creation option in the Leonardo dashboard you'll see a prompt box at the top of the page I write click and paste the first image prompt copy from chat GPT into this box from the left panel in the preset drop- down select the Phoenix 1.0 model which is Leonardo's latest image generation model in the prompt enhanced T drop down select off in the preset style section choose Dynamic set the generation mode to fast for image Dimensions since I want this video in horizontal long format for YouTube I select a 16 to9 ratio I set the image size to medium the number of images generated in each step is set to four Once all settings are done click generate my request is cued and after a
4:37 very short time the images are generated four thumbnails are displayed I click on one of the thumbnails to review the images there might be issues in image generation and if you are not satisfied with these images you can change the settings and regenerate new images I am very satisfied with this image and want to download it the download button is below the image frame our animated Story begins with this image we repeat the previous process I return to chat GPT copy the image prompt for the second scene and again paste it into the Leonardo image prompt box with the same previous settings I click on generate again my request is cued and after a few seconds new images are
5:23 generated four thumbnails are displayed I click on one of the thumbnails to review the images I am not satisfed ified with these images and believe Leonardo can generate much better ones I repeat the image generation process I click generate and after a very short time the images are generated four thumbnails are displayed I click on one of the thumbnails to review the images one of the images is good and I download it before creating the next scenes image let me tell you something click on the three dot icon at the top right corner of the images and select copy seed this command copies and saves the seed number it ensures that the character's form remains consistent for subsequent images after this go to the advanced settings in the side menu and enable the use fixed seed option paste the copied seed
6:10 number into the corresponding box this ensures the creation of a consistent character form across scenes keep these tips in mind while creating images with Leonardo AI we repeat the previous process I return to Chad GPT copy the image prompt for the third scene and again paste it into the Leonardo image prompt box without Chang changing the previous settings I click generate my request is cued and after a few seconds new images are generated for thumbnails are displayed I select one of the thumbnails review the images and download the one I like for the third scene we must continue this process for the remaining scenes copy the image prompts for the subsequent scenes from chat GPT paste them into the Leonardo prompt box and generate the images reviewing the images you will see that
6:55 the characters remain almost identical with different backgrounds and scenario I for each scene as demonstrated following this method ensures the character does not change you can create images with Leonardo for free you receive 150 free tokens daily which are replenished the next day if this is insufficient you can opt for paid plans which are not too expensive the work must proceed in the third step the images generated by Leonardo AI are converted into videos and animations using AI called clling visit the clling AI website click on try now under the clling trial package option however if this option is unavailable click on the signin button at the top right corner of the site to create an account and log in if you have already created an account simply enter your email and password and
7:42 click sign in otherwise click sign up for free enter your email and password then click next a window named security verification will open featuring a puzzle piece drag the slider connected to the puzzle piece to the empty slot to complete the puzzle once done a verification code will be sent to your email check your email retrieve the code and enter it in the verification code box click sign in and you will be logged into the clling AI website upon creating an account you will receive many free tokens to use the website services from the top right corner of the website you can access your account and its details from the left menu click on the AI videos item from the right section access the archive panel of images and videos created with clling AI on the new page you will see two tabs text to video
8:29 and image to video in the left panel click on the image to video tab through this panel you can upload images in jpg and PNG formats up to a maximum size of 10 mbes and a minimum dimension of 300 pixels to do this click on the upload icon in the center of the box in the opened window select your desired image and upload it after uploading the thumbnail of the image will be displayed in the panel then in the prompt section you can type your ideas for animating the image and the animation will be created based on your idea skip the motion brush section as this feature requires a separate tutorial further down in the setting panel there is a slider that allows you to choose between creativity and relevance in this case I don't change this item in the mode
9:14 section the standard mode is offered in the free plan and enables faster generation speed while the professional mode provides better visual quality but is only accessible through the Premium plan which requires purchasing the Premium plan in the duration section you can set the video length between 5 and 10 seconds however the 10-second duration is only available in the Premium plan the camera movement option in the image to video section is currently disabled but is expected to become available in the near future in the negative prompt box you can specify items you don't want in the scene click on the generate button again 10 tokens will be deducted from your credit my request is cued and after a short while my image is converted into a video and displayed now I play the video below the
10:00 video frame there is a download button to get the video for free on your device however note that videos in the free account have watermarks to download Watermark free videos you need to purchase the Premium plan if you are not happy with the generated video test and adjust the settings several times with multiple attempts you will surely achieve an excellent video generation this process needs to be repeated for all images after creating the story and converting the images into videos and animations the story must be narrated by a voice actor now we need a narrator's voice you can record the story text yourself using a professional microphone but if you don't have the resources don't worry there's another option using AI generated voices search for the 11 Labs AI website on Google and visit it 11 Labs aai
10:47 offers a text to speech feature that allows your text to be read by various narrators creating an account on this website is free you can log in using methods like entering your email or using a Google account I click on sign up with Google select one of my Google accounts and log in after logging in some questions are asked which I skip now I return to chat GPT copy all the voiceover sections and paste them into the text to speech section of the 11 Labs AI website from the right panel in the drop down list voice you can change the narrators voice listen to various voices and choose the one most suitable for
11:33 your story then click on the generate speech button and the work is done next to the generate speech button there is a download button to get the narrator's audio file now the story animations and narrator's voice are ready and we move into the editing phase we need to combine them to create a long video and based on our story make a full length animation you can edit using cap cut or free tools like canva I use Adobe Premiere Pro for my projects and I recommend you learn it too in Adobe Premiere Pro I first create a new project you need to name this new project and specify it save location click create now a new project is created right click in the project panel and use the import option to bring the animations into the project panel repeat the same for the audio files importing
12:19 them into Premiere Pro from the file menu execute the create sequence command to make a new sequence Define the sequence dimensions and assign a name this way we create a timeline to combine the materials drag and drop the videos onto the timeline the clip mismatch warning window will appear here choose keep existing settings select all video layers rightclick on one of them and choose scale to frame size this ensures the video Dimensions match the sequence Dimensions here I arranged the short videos and the timeline sequentially to combine them into a long video based on the story I also add the narrator's audio file to synchronize the video with the narrator's voice use the razor tool to split the audio track this allows placing the narrator's voice exactly at the correct points to match the
13:11 video after this click export name the output file and set it save location in the format section set the output to h264 in the preset section set the output size and dimensions to full HD now click the export button after a few minutes my long video video is ready if you are interested in video editing with Adobe Premiere Pro let me know in the comments if there are many requests I will create tutorials for it if you found this tutorial useful don't wait hit the like button and share this video with your friends we've gone all out for you here it's time for you to show your support too a vast number of exclusive AI tutorials will soon be uploaded to the channel so subscribe and turn on the notification Bell so you don't miss anything AI is changing the world do you
13:57 want to be a spectator or a part of this revolution the next tutorial will Amaze you so stay tuned
