How to Create Films Known from 'Balenciaga' Memes - Step by Step (Film, 7 Minutes)
In the latest video from PromptJungle, the creator shares tips on how to create viral Balenciaga-style AI animation videos. While many creators charge for their prompts, PromptJungle has decided to provide everything for free. All they ask is that viewers like the video to help it reach a wider audience. The video uses a Harry Potter-themed example to illustrate how to create engaging content, and also includes links in the description to short beginner's guides, making it accessible for anyone interested in experimenting with AI content creation.
In the first part of the tutorial, PromptJungle explains how to use ChatGPT and Mid Journey to generate images of Harry Potter characters. The creator provides exact commands for ChatGPT to obtain character lists and Balenciaga clothing that suits the 1990s aesthetic. The process involves communicating with the AI model and providing it with proper instructions, making this method accessible to anyone with access to these tools.
Next, viewers learn how to use Discord and Mid Journey to create graphics that resemble the movie characters, with appropriate styling. PromptJungle emphasizes the importance of selecting characters carefully and giving the AI correct instructions, which significantly affects the quality of the final project. Additionally, they remind viewers of the option to upscale images using online tools to achieve better visual quality.
The further section of the tutorial focuses on generating audio for the videos. PromptJungle showcases how to search for and use a voice actor, like Daniel Radcliffe, to create a suitable voiceover for the characters. It also provides information on how to convert mp3 files from YouTube and add voice in voice cloning tools. This allows viewers to create a unique narration that brings their animations to life.
At the end of the tutorial, PromptJungle describes how to bring everything together using CapCut. They highlight how to apply transition effects and animations to create a dynamic and visually appealing film. The video is quite popular, boasting 1,931,309 views and 90,529 likes at the time of writing this article. This is a great testament to the fact that AI-themed content captures viewer attention and serves as an inspiration for other creators.
Toggle timeline summary
-
Introduction to creating viral Balenciaga AI animation videos.
-
Offers free prompts for video creation.
-
Encourages viewers to like the video for wider reach.
-
Mentions links to additional resources in the description.
-
Uses a Harry Potter by Balenciaga video as a tutorial example.
-
Introduction to tools ChatGPT and Mid Journey for image generation.
-
Instructions to get popular Harry Potter character names using ChatGPT.
-
Instructs to mimic a Balenciaga fashion designer.
-
Details commands for generating fashion sketches.
-
Clarifies the need for a main prompt for generating images.
-
Guides users on how to use Mid Journey to create images.
-
Instructions on how to feed prompts in Mid Journey.
-
Suggests refining prompts if generated images don’t fit the theme.
-
Recommends using upscale.media for image resolution enhancement.
-
Transition to generating audio for characters in the video.
-
Steps to convert YouTube audio of the character's voice to mp3.
-
Introduction to animating characters using DID.
-
Instructions for adding voice and generating animation videos.
-
Discusses adding background music from a linked source.
-
Intro to editing video clips using CapCut.
-
Final editing techniques like adding dynamic zoom and transitions.
-
Concludes with suggestions for sharing tips in comments.
Transcription
So, let me show you how to make these viral Balenciaga AI animation videos. Many creators charge for the prompts, but I'll share everything for free. All I ask is for you to like this video so it can reach more people, as it really helps the channel. I'm going to link everything down in the description. And I will also link some short beginner's guides for the tools if it's your first time using them. I'm going to use the Harry Potter by Balenciaga video as an example in this tutorial. Okay, let's start. To generate the images, we will use ChatGPT and Mid Journey. I will share the main prompts in the description as a list, so it's easier for you to copy and paste. First, go to ChatGPT, open a new chat, and type, Give me the 10 most popular Harry Potter characters, just the names. After that, paste this prompt. Now, act as a Balenciaga fashion designer with 20 years of experience. I want you to dress each of these 10 characters in a unique Balenciaga piece for a runway show. Just write the name of the character and the piece. Remember, it's a 1990 fashion show. When it has finished matching the clothes with the characters, we need to give it an example of our main prompt. So paste the next prompt you have in the list. Okay now this is a prompt that I use to generate images from another AI image generation tool called Mid Journey. 1990 screengrab of female model Hermione Granger, wearing a grotesque black Balenciaga dress. Fashion movie scene? Balenciaga commercial R3 colon 2 V5. Just say yes if you understand. After that, paste the next prompt, which will tell it to generate 10 prompts for your images that you will generate in Mid Journey. Now, head to Discord to use Mid Journey. Log in and go to the Rookie channel and start feeding those prompts one by one. Type slash imagine and paste your prompts. Choose the ones you like and upscale them. If you start getting images that don't resemble the character's facial features, you can always delete the part where it says male or female model. Also, if you start getting clothes that don't match the theme of the video, you can go back to chat GPT and instruct it to rewrite the prompts with a theme in mind, like goth, grotesque, or even colors like only black and white. Go through all your images and download the ones you like. Always envision the video while you are choosing your images for the best outcome and a higher quality content. If you're not happy with the quality of the images, head to upscale.media to get a better resolution for your images. Click on upload image. And sign up so you can bulk upload. Choose the free plan and upload all your images. Then click storage, select all your images, and click transform. Scroll down and click upscale. Choose your scale, I'm going to choose times 2, as I think that's enough, and click export into a zip file. Download your images when done. Now, let's generate the audio part. Choose the characters that will talk in your video. I'm going to do Harry Potter. So go to YouTube and search for Daniel Radcliffe voice for 1 minute. Find a good quality sound in the video and copy the link. Head to YouTube to mp3 converter and convert and download the mp3 file. If the file is too long, or you want to isolate a part of the file, head to an mp3 cutter and cut and download the part you want to use. After that, go to 11 labs and click voice lab. Then, add voice. Instant voice cloning. And upload the mp3 file of your character. Click, add voice. Then, use it to generate your script and download the generated voiceover. Do this with all the characters that will speak in your video. Now for the animation part. Head to DID and sign up. You have 20 credits for free. Click, create video. Then, add. And choose your first character. We will do two different animations. The first one is animating the speaking characters, so toggle to audio. Upload the voice of the file, and click, generate video. Download the video when ready. Do this with all your talking characters. After that, we need to animate all the other characters in our video, both talking and silent. This time, toggle to script instead and click on the clock icon. Which indicates a pause of 0.5 seconds. So I will choose 6 pauses, which totals 3 seconds. No need to do anything else. Just hit, generate video. Do this with all your characters. When done, download all the clips. For music, if you want to use the same legendary background track that everyone uses, I've linked it in the description. But remember that you will need consent to use it on your YouTube channel. You can find the copyright for it on Epidemic Sounds, which I'll link as well. Now, to put the whole video together, you can use any software you're comfortable with. I'm going to show you how to do it with CapCut because it's free. And you can do the camera flash effect easily. You can use it on your browser or your phone. I'm more comfortable using it on the phone. So, open all your clips and reorder them as you wish. Add your background track. And to make the flash effect. Choose the place on your timeline and split. Then tap on, transition. And choose light. Then, flashes. After that, go to audio, then effects, and find the camera shutter 2 effect. Align it under every flash transition. Make sure to have a dynamic zoom in every clip as it makes the scene more alive. To do that just put one keyframe at the start of the clip and another at the end of the clip. And have an end zoom position of the clip. And you're done. This is how it will look like. If you know any other shortcuts or ways that are better or easier to do any part of this tutorial. Please don't hesitate to share it in the comment below with the others. And if you found this helpful. Don't forget to like the video, and maybe subscribe. As always, see you in the next one.