Child EnlightenmentShort VideoIt's a very hot track both in the past and now! There's an account that focuses on making AI ancient poetry starter videos that is growing extremely fast.
From 225,000 followers and 305,000 likes when I first followed the account, I managed to get 136,000 followers and 220,000 likes in just a month and a half.
With an enviable fan base of 361,000, only 72 videos were released. Of these, the one video that topped the Jitterbug platform alone garnered 295,000 likes, and that's just from Jitterbug, not yet counting the heat from other platforms yet!
Nowadays, parents love to show their children this traditional cultural content, which is very easy to do with AI.
This kind of account start number speed like a rocket, want to do children's education direction can follow me to dismantle this play!
▌Step 1: DeepSeek to help us come up with selections
We use the Tencent metaplot that accesses the DeepSeek-R1 model to help us come up with selections.
Website: https://yuanbao.tencent.com/chat/
Enter the following command directly:
I'm going to make an AI Ancient Poetry video for babies aged 0-6 years old, but I don't know which ones are for 0-6 years old, can you please help me to recommend 10 ancient poems.
option[Deepseek]Model, open[R1 - Deep Thought]switch, click the arrow button to send the command to Tencent Meta.
Waiting for a few moments Tencent meta gives the following results:
Here I chose "Winging the Goose" by Luo Binwang to create a video.
▌Step 2: DeepSeek Generates Ancient Poetry Splits
Let's continue to send commands to Tencent Meta:
I want to make an AI video about the ancient poem "On the Pool", help me design the sub-script for each line of the ancient poem, including scenery, dribble, text, screen, timeline, and output it as a table.
Tencent Yuanbao directly generated a table of sub-scene description. The table includes the timeline, the original poem, the scene, the way of transporting the mirror and the description of the screen, and the initial framework of the whole video content is completed.
▌Step 3: DeepSeek Generates Painting Cue Words
Next, we'll have Tencent Yuanbao generate the subplot as an AI painting cue word to make it easier to go to the AI painting tool to generate the image.
We're still sending commands to Tencent meta:
Help me to generate the AI painting prompts for the "Winged Goose" ancient Chinese Poetry Scene Script. Containing the subject, scene, style, quality words, each cue word at the end of the "ancient Chinese cartoon, bright colors, 3d Pixar style", the cue word should be simple and easy to read, do not contain complex descriptions, do not have adjectives and lyrical part, please describe the subject's appearance (fixed), behavior. Then according to the descriptor to generate the picture to video prompt words, prompt words on the logic of what the subject do, in the form of table output.
Here are the results obtained:
We optimized the cues a little bit to get the following painting cues and image to video cues:
Subtitle 1: Goose, Goose, Goose
Painting Prompt Words:Three white geese, round fat body, orange flat beak, short neck, reeds by the lake, sunlight hitting the water, fluff clearly visible, ancient Chinese cartoon, bright colors, 3d Pixar style
Image to video cue word:Three geese take turns peeking through the reeds, and the aerial camera pushes forward.
Subtitle 2: Singing to the Sky
Painting Prompt Words:Three white geese, round fat body, orange flat beak, short neck, reeds by the lake, sunlight shining on the water, fluffy feathers clearly visible, white geese stretching their necks, beaks open Blue sky and white clouds background, rainbow arc, neck bending arc naturally, ancient Chinese cartoon, bright colors, 3d Pixar style
Image to video cue word:Goose neck swinging from side to side, 360 degree surround shot
Subtitle 3: White Hair Floating on Green Water
Painting Prompt Words:Three white geese, round fat body, orange flat beak, short neck, lake reeds, sunlight on the water, fluff clearly visible, white goose body floating, goose paws immersed in the water, transparent lake water, underwater green water plants, clear reflection on the water surface, ancient Chinese cartoon, bright colors, 3d Pixar style
Image to video cue word:The goose's body rises and falls with the water waves, and the horizontal panning follows the shot.
Subtitle 4: The Red Palm Pushes Back the Clear Wave
Painting Prompt Words:Three white geese, round fat body, orange flat beak, short neck, reeds by the lake, sunlight shining on the water, fluff clearly visible, goose palms open paddling, water ripples spreading, underwater perspective, water ripples are real, ancient Chinese cartoon, bright colors, 3d Pixar style
Image to video cue word:Goose paw paddling creates swirls, water plants swaying from side to side, swooping and then following up with a goose paw shot
▌Step 4: Instant Dream AI generates images
Open the Instant Dream AI homepage: https://jimeng.jianying.com/ai-tool/home
Use ShakeScan or cell phone verification to log in and select the[Image Generation]
Enter the Ancient Poetry Split 1 prompt words generated in the previous step into the description field.
Raw graph modeling:Pictures 3.0, picture scale:9:16Click[Generate Now]
Wait for the generation to finish and then continue if there are no satisfactory images.
Click below if you are satisfied with any of the pictures[HD]button to generate a high-resolution image.
After the HD image is generated, click on the image again and select the[Goes to canvas for editing]
Click[Right Mouse Button] - [Save as Picture], save the image locally.
Follow the above instructions to generate other split images.
▌Step 5: Conch AI Chart Generation Video
Tusheng video I use here is the conch AI, of course, namely dream AI, Keling AI or Vidu AI can also be, partners can try them all, which effect is good to use which.
Conch AI website: https://chat.minimaxi.com/
Go to the home page and click on[Conch Video]
option[Video Generation], enter the Toussaint video interface.
Upload the Split 1 image generated in the previous step, then enter the corresponding image-to-video cue word obtained in the third step, and click the button with the[Shell icon]of the Generate button to start generating the video.
Use the same procedure to generate other split videos, after which click on the[Download Icon], download and save the generated video.
▌Step 7: Generate Ancient Poetry Music
For text to music AI tools we use Sponge Music at https://www.haimian.com/
Go to the website and select[Composition] - [Customized Lyrics, type in the complete verses of "Winging the Goose", set the music style, and then click on the following[Generating Music]button.
The music is generated and now satisfactorily downloaded and saved locally.
▌Step 8: Edit the video
Open the cutscene, import the created video subplot and music into the cutscene and add them into the track in order, add subtitles, make a little detail adjustment and you're done.
By this point the video is complete, click on the top right corner[Export]Set the export parameters, save it locally and publish it to various platforms!