Two days ago, a fan sent in aTubing ChannelAsk me if the AI did it.
When I looked at it, the content of this number was simple: a beautiful young lady dressed in a cool outfit and playing jazz at the mixing desk.
Started 3 months ago, 26 videos, already 12.3K followers, and all of these in the picture areAI made the DJ lady.Each video is about an hour long and, crucially, has good traffic, with 10,000 to 100,000 views each.
Classmates again asked for advice on exactly how to do it , and here's my replica of the Netflix DJ.
The original account is obviously a beauty alchemized with native Stable Diffusion, the graphics card costs at least several thousand, and requires not only a high computer hardware configuration, but also a local ride model.
It's just so not newbie friendly!
So, in this installment of the tutorial, I'm going to give the full process directly from creating the static image to the beautiful woman swinging up to the music generation
No skills required, all free software used!
Video with AI is categorized into text-born video and graph-born video.
Chart-born video is now a more mature approach, so to make a video you first need a chart, and to make a chart you must have a drawing cue word.
firstGenerate mapping cues
We found benchmarked accounts and had AI analyze one of the account's most trafficked images to generate mapping cue words.
Speaking of image analysis, the world's most powerful is Google's gemini pro, (not convenient to use gemini users can use kimi instead, kimi recently upgraded the image analysis function) open aistudio.google.com, find gemini 1.5 flash, now you can also use the just released 2.0 flash, make a request! Request:"Analyze this photo."
gemini is analyzed in Chinese as follows:
Because we need to use foreign AI drawing software, Chinese support is not too good, I asked it to translate to English, and got the following prompts
"The image shows a Young Asian woman , lost in the rhythm, her headphones obscuring her ears as she works the DJ decks. Clad in a dazzling rainbow low V dress,low V , her concentration is palpable. Clad in a dazzling rainbow low V dress,low V , her concentration is palpable. A stylish spiral staircase and strategically placed speakers complete the scene. "
DIRECT TRANSLATION: This image shows a young Asian woman, immersed in the beat, her headphones covering her ears as she operates the DJ booth. Her concentration is evident as she wears a dazzling rainbow low V-neck dress with a low V-neckline. A sleek spiral staircase and strategically placed speakers complete the scene.
Let's go to the drawing board.
I used Google's latest drawing AI imagen 3, the prompt word remains unchanged, you can use flux (silicon-based), that is, the dream, can be Ling to do the map can be, the actual test results are as follows, Flux I think the over simulation.
Imagen 3 was just released at labs.google/fx/tools/image-fx
Do the video again.
Here to use the latest Keling 1.6, the actual test should be the strongest graphic video AI, before the conch AI used more, Keling 1.6 out, conch suddenly do not smell, Keling is currently sent to the free users 66 points per day, quality upgrade, the price remains unchanged, 5 seconds of HD 30 points, 10 seconds 60.
Since the DJ has little movement, we'll just use 10 seconds and repeat.
Make music with AI again.
Because it is a DJ, there must be music, we log in suno, suno upgraded to V4, select V4, select pure music, enter the prompt word "JAZZ".
Of course, you can also use the music generation of the instant dream, and finally, synthesize it with editing software such as clipping, Tencent Zhiying (zenvideo.qq.com), done!
How do you dress a DJ beauty differently, you may ask?
Simple, AI-enabled fitting
Ten seconds. Clothes change.
You can also adjust the cue words in the first step to modify the clothes, the posture, and in addition to the beautiful DJs, we can also try other ways of playing, such as taking it a step further, lip-synching, and so on.
Found it?
You've seen a lot.Short VideosExplosive play, traffic code is these '
First, the needs. Beauty, Education, Health, Nationalism, Reading
Second, technology. Technology iterates, new features come out with better results and bring about scene changes. As I said in the "high-speed rail mask beauty", people are sexy beauty, but although their clothes are sexy, but the style is simple. And you will AI change clothes, global fashion, want to let the mask beauty wear which can be. You'll be able to differentiate yourself.
Third, the scene. Just look at the beauty can not, but also have a scene, such as today's DJ, the Internet popularity of the Buddha Yuan, kitchen Yuan, what is the demand for the implementation of the scene.
Beautiful DJ, you can also do AI beautiful car model series, look at the effect of Imagen 3 as a car model.
