After the Barbieheimer phenomenon exploded online a few days ago, many netizens have been “reproducing” the magical technique of making movies using MidJourney+Gen-2!
A netizen updated their tutorial, stating that creating Barbieheimer only takes 7 steps, and it was praised by Karpathy as “Film Production Industry 2.0”.
A 20-second animation short film with a complete plot and 6 shots can be completed in 7 steps, even Cao Zhi would call it professional!
Complete Barbieheimer in 7 Steps with Stunning Effects
1. ChatGPT helps you write the storyboard script and also write the subtitles.
2. Based on the storyboard script, use Midjourney to generate the first image for each shot.
This may be the only step in the 7-step process that has a bit of a barrier, as you need to create your own prompts for each image.
However, after clicking on the image to enlarge it, you can see that the prompts are not very long, and friends with a basic knowledge of English can easily try it out.
These are the starting images for several other scenes in the short film, all generated using Midjourney.
3. To ensure the color tone of the scenes in the short film is consistent, you need to adjust the color tone of each image using photo editing software.
For example, if the tone of the short film is more retro, the original images generated by Midjourney may not match.
After adjusting with any photo editing software, all scenes can have a more consistent style.
4. Use Gen-2 to animate each photo, turning the 6 photos into 6 shots.
5. Then use ElevenLabs to generate the voice for the subtitles.
6. Then use FinalCut Pro to combine the animation, sound, and effects, and the short film is basically complete.
7. Finally, use Capcut to add subtitles, and you’re done!
Experience and Insights After Testing
The biggest obstacle is that because Gen-2’s animations can only be randomly generated from one image, there tends to be a lot of distortion when it comes to facial images.
I originally wanted to make a video of Boss Ma crafting a starship, but I found that the facial distortion was too severe, resulting in the first frame of each video being Boss Ma, but after one second, it was impossible to tell who it had turned into.
Therefore, if you want to use Gen-2 to make a video related to a celebrity, it is still almost impossible at this point.
Moreover, these facial distortions and character movements are completely random and not under user control.
A netizen made a video by taking a screenshot of the last frame every 4 seconds and letting Gen-2 continue generating new animations.
After about 40 seconds, the character in the video went from a comic-style animated character at the beginning to almost a sculpture at the end.
Even if there are some obvious dynamic effects in the images, Gen-2 still cannot understand them, so the generated effects may not meet your expectations.
The character’s movements cannot be well controlled either; it may take a long time to try with the same image to generate a satisfactory animation.
So based on the current capabilities of Gen-2, it is still unlikely to adapt to more complex scripts at will.
This requires avoiding close-ups of human faces and similar scenes when writing scripts.
However, if in the future Gen-2 can completely combine prompts and images, allowing images to move according to the prompt descriptions, the effects will have a huge leap.
Other Effects of Midjourney+Gen-2
The master Guizang used Gen-2 to create several scenes from Oppenheimer, which are enough to confuse the real with the fake.
At the same time, he also compared the differences between similar scenes and those generated by Pika Lab.
The image below shows the effects of Pika Lab.
In addition to the initial segment of “Barbieheimer”, many netizens have also started using Gen-2 and Midjourney as a golden duo to develop animation as a side business.
Let’s appreciate some impressive animation effect demonstrations.
It can be seen that in the demonstrations, the facial deformation is not very significant, which is a big difference from the actual tests. This is likely because the author found effects with less facial distortion after trying many times.
A netizen generated a trailer of a famous Marvel character, which looked very realistic. With some animation effects and lighting, it really felt like an official Marvel work.
This is a trailer of a horror movie generated by a netizen, which effectively utilized the character image distortion of Gen-2, enhancing the horror atmosphere.
This segment is also an artful video made by a netizen using MJ+Gen-2, with updated directorial camera effects in post-production.
This is an animation generated from a static oil painting, although there is a bit of distortion, the effect is indeed good.
Shenzhen Longgang Intelligent Audio-Visual Research Institute
Artificial Intelligence | Ultra HD
Industry Innovation | Technology Incubation | Achievement Transformation