Wan2.1 is the hottest open-source video generation model recently, with powerful AI-generated video capabilities that outperform other AI video generators. It also offers AI text-to-video capabilities, making it easy to create AI videos from text prompts using advanced tools and techniques. MimicPC provides various Wan2.1 video generation workflows, including text to video and image to video ready-to-use workflows.
AI Video Generator Prompt Formula
Text prompts are used to describe the content and motion process in videos, serving as the key factor in controlling video content and effects. Utilizing a text prompt allows users to quickly transform their textual descriptions into complete videos. The more complete, precise, and rich the prompt description, the higher the quality of the generated video and the closer it matches the expected content. To help you get started faster, we provide four prompt formulas for different usage needs:
Basic Formula
Suitable for new users trying AI video for the first time, and users who use AI video as inspiration. Simple and free prompts can generate more imaginative and engaging videos.
Prompt = Subject + Scene + Motion
- Subject: The subject is the main object featured in the video content, which can be a person, animal, plant, item, or an imaginary object that doesn’t physically exist.
- Scene: The scene is the environment where the subject is located, including background and foreground. It can be a physically existing real space or an imagined fictional setting.
- Motion: Motion includes both the specific movements of the subject and non-subject movement states. It can be stationary, small-amplitude movement, large-amplitude movement, partial movement, or overall dynamic motion.
Advanced Formula
Suitable for users with some AI video experience. While AI tools can assist in generating videos, having video editing skills can significantly enhance the final output, making the content more engaging and professional. Adding richer and more detailed descriptions on top of the basic formula can effectively enhance video quality, vividness, and storytelling.
Prompt = Subject (Subject Description) + Scene (Scene Description) + Motion (Motion Description) + Camera Language + Atmosphere Words + Style
- Subject Description: Subject description details the appearance features of the subject, which can be listed through adjectives or short phrases. For example, “a black-haired Miao minority girl wearing ethnic clothing” or “a fairy from another world, wearing tattered yet magnificent clothing, with peculiar wings made of rubble fragments unfolding behind her.”
- Scene Description: Scene description details the environmental features where the subject is located, which can be listed through adjectives or short phrases.
- Motion Description: Motion description details the characteristics of movement, including the amplitude, rate, and effects of the motion. For example, “violently swaying,” “slowly moving,” “shattering the glass.”
- Camera Language: Camera language includes shot size, angle, lens, and camera movement. Common camera language terms can be found in the prompt dictionary below.
- Atmosphere Words: Atmosphere words describe the expected mood of the scene, such as “dreamy,” “lonely,” “majestic.” Common atmosphere words can be found in the prompt dictionary below.
- Style: Style describes the stylistic language of the image, such as “cyberpunk,” “line drawing illustration,” “post-apocalyptic style.” Common styles can be found in the prompt dictionary below.
Camera Movement Formula
Suitable for users who have specific requirements for camera movement and face professional video output scenarios. Adding more specific camera movement descriptions on top of the basic/advanced formula can effectively enhance the dynamic feel and narrative quality of the video.
Prompt = Camera Movement Description + Subject (Subject Description) + Scene (Scene Description) + Motion (Motion Description) + Camera Language + Atmosphere Words + Style
- Camera Movement Description: Camera movement description specifically describes camera motion. On the timeline, effectively combining camera movements with changes in content can enhance the richness and professionalism of video storytelling. Users can imagine and write about the camera movement process by assuming a director's perspective. In terms of timing, it's important to reasonably control the duration of camera movement within 5 seconds and avoid overly complex camera movements.
Transformation Formula
Suitable for users with specific creative needs in this category. Adding transformation descriptions on top of the basic/advanced formula can effectively enhance the fun of the video and bring unexpected visual effects. Using AI tools, users can easily generate video content by inputting a detailed description and clicking a button, making the process efficient and customizable. Utilizing various video editing tools can streamline the video creation process, making it more efficient and customizable.
Prompt = Subject A (Subject Description) + Transformation Process + Subject B (Subject Description) + Scene (Scene Description) + Motion (Motion Description) + Camera Language + Atmosphere Words + Style
- Subject A: Subject A refers to the features and state of the subject before transformation.
- Transformation Process: Transformation process describes how the subject changes from form A to form B. Detailed process descriptions can effectively enhance the naturalness and vividness of the transformation.
- Subject B: Subject B refers to the features and state of the subject after transformation.
Example Prompts in Different Dimensions
Through writing prompts in different dimensions, you can enhance the controllability and expressiveness of generated videos in specific dimensions, making it an essential practice for video content creation. We have carefully prepared examples of commonly used dimensions and prompts as references, and also welcome everyone to discover more tips and tricks. Mastering video editing techniques can greatly enhance the quality and storytelling capabilities of your generated videos.
1. Shot Size
Type | Prompt Example |
Close-up | Close-up shot | In the video, the camera focuses on the face of a woman in ancient style, soft light falls on her skin, outlining delicate contours. |
Medium Close-up | Medium close-up shot | In the video, the camera shows a woman in ancient style holding a green folding fan, her fingertips gently brushing over the exquisite patterns on the fan surface, as if savoring its charm. |
Medium Shot | Medium shot | In the video, the camera shows a woman in ancient style gracefully walking among flowers, her long dress fluttering in the wind, as if merging with nature. |
Long Shot | Long shot | In the video, the camera shows a bustling city street, with people coming and going on the wide sidewalk, forming a vivid and lively scene. |
Bird's Eye View | Bird's eye view shot | In the video, the camera uses a bird's eye view angle to look down on the entire city, showing the intertwining streets and buildings. |
2. Angle
Type | Prompt Example |
Low Angle | The video starts with a pair of walking legs, the camera shooting from a low angle, focusing on the movement of the feet. In the frame, shoes step on the rough abandoned ground, surrounded by broken concrete and scattered weeds, showing the desolation and decay of a post-apocalyptic style. |
High Angle | The video shows a scene of a person walking in the post-apocalyptic world, the camera shoots from above a person slowly walking in a post-apocalyptic scene with sunlight. |
Drone | FPV drone perspective | The video begins with an FPV (first-person view) drone shot, bringing an immersive feeling. The camera quickly flies between the city's skyscrapers, showing the magnificent urban landscape. Buildings flash by quickly, with light and shadow intertwining, reflecting the modernity and prosperity of the city. |
3. Lens
Type | Prompt Example |
Fisheye | Fisheye lens | The video shows a scene under a fisheye lens, the camera uses a fisheye perspective, bringing a unique curved effect that makes the busy city street more eye-catching. The wide view makes viewers feel as if buildings are tilting towards the sky, the high-rises on both sides of the street appear especially magnificent and three-dimensional under the fisheye lens, the distorted lines create a strong visual impact, fully showcasing the city's vitality and hustle. |
Wide-angle | Wide-angle lens | The video captures a busy city street surveillance scene with a wide-angle lens, with a broad frame and expansive view. High-rises line both sides of the street, traffic flows continuously, and pedestrians stream by, showing the hustle and vitality of city life. |
4. Camera Movement
Type | Prompt Example |
Push In | The video shows a huge cubic stone block, standing in the center of a square, with silence around it. The camera slowly pushes in, gradually approaching the stone block, with rough textures and traces of time becoming increasingly clear. |
Pull Out | The video shows a huge cubic stone block, standing firmly in the center of a square. The camera slowly pulls out, the magnificent outline of the stone block gradually emerges, the stone tiles of the square and the surrounding lawn gradually appear. Finally, the entire view of the square is presented before the eyes. |
Pan | The video shows a cubic stone block, the camera focuses on it, with sunlight shining through, emitting a warm glow. As the camera gently moves, the details of the block gradually change in the view, with the surrounding environment blurring into the background. Then, the camera naturally switches to the cubic iron block beside it, the smooth metal surface sparkling in the sunlight. The focus smoothly transitions, creating a stark contrast between the coldness of the iron block and the heaviness of the stone block. The camera moves between the two, showing their unique charm. |
Follow | The video shows a cubic stone block rolling in the center of a square, with the camera following the movement. As the gravel moves, the surrounding grass is lush green. The camera flexibly sticks close to the gravel, capturing the subtle lines on the ground and the dynamic sense of the spring breeze passing by. |
Orbit | The video shows a huge cubic stone block, standing in the center of a square. The camera rotates and extends, circling around this block, capturing the rough texture on the surface and the subtle sparkle in the sunlight. |
5. Speed
Type | Prompt Example |
Slow | The race car moves slowly, the background gradually becomes clear in the tranquility, everything seems to be stretched by time. The car speed is gentle, bringing a kind of leisurely experience and inner peace. The driver, as if integrated with the surrounding environment in this serenity, shows a concentration that inspires awe. |
Fast | The race car drives quickly, the background blurs in an instant, everything seems to become an intersection of colors. The rapid speed makes people feel intense stimulation and a surge of adrenaline. The driver, as if controlling the entire world in this roar, releases a passion that makes people's blood boil. |
Slow Motion | People move slowly, slow motion magnifies every pedestrian's steps, people and environment blend together, highlighting every detail of life. The pace is slow yet rhythmical, as if telling the story of the city, carrying thoughts and insights, sharing the poetry of life. |
Time-lapse | The video shows the amazing process of plants growing and blooming with a time-lapse effect. In the frame, buds experience growth and blooming in just a few seconds, from tender buds to vibrant flowers, instantly dazzling viewers. Each stage is clearly captured, showing the vigor and beauty of life, making people marvel at the wonder and magic of the natural world. |
6. Atmosphere
Type | Prompt Example |
Vitality/Joy/Pleasant/Beautiful | The video shows a vibrant forest, sunlight shines through the canopy casting golden spots of light, birds fly joyfully among the trees, crisp calls echo in the air, as if singing hymns for this thriving world. Leaves sway gently in the breeze, like dancing happily to the rhythm of music. The thriving scene brings joy to the heart. Small animals frolic on the grass, flowers bloom in the sunshine, the entire forest is full of life and vitality, as if telling the beauty and infinite possibilities of life, making people feel the vigor and hope of nature. |
Deep/Soft/Quiet/Dreamy | The video shows a deep forest, the tranquility of the night like a soft veil, gently covering every inch of land. Silence all around, as if time has frozen at this moment, only the breeze gently brushing the treetops, bringing slight rustling sounds, as if whispering with nature. The night sky is like deep blue velvet, stars twinkling like distant jewels embedded in it, emitting a cold yet soft light. The entire scene appears quiet and harmonious, refreshing the spirit, as if entering a dreamy realm, seemingly isolated from the world, fully immersed in this embrace of nature. |
Lonely/Desolate/Melancholy/Tranquil | The video shows a lonely forest, silence all around, as if time has stopped at this moment. Leaves fall gently, slowly spreading on the ground, making faint rustling sounds, as if quietly telling the farewell of autumn. Only the sound of wind echoes lonely in the empty space, seemingly awakening this silent land. Shadows cross between trees, creating a desolate and melancholic atmosphere. The entire scene carries a hint of solitude, making people feel a light melancholy, as if paying tribute to lost time, deep in this tranquility, it makes one ponder. |
Tense/Uneasy/Oppressive/Gloomy | The video shows a tense forest, fierce winds rage, violently blowing the treetops and leaves, making deep rustling sounds, like nature whispering uneasy omens. Tree trunks sway, as if fighting against this sudden authority. In the sky, dark clouds gather, the heavy cloud layer like an oppressive mood, covering the entire picture, giving a gloomy and heavy atmosphere. Everything around seems to be holding its breath for the coming change. The entire scene is full of urgency, making one's heart slightly tighten, as if a storm that cannot be predicted could break out at any time, making people feel the ruthlessness and power of nature. |
Solemn/Powerful/Majestic/Awe | The video shows a solemn forest, trees tall and straight, standing on the earth like guardians, emanating a silent power. Sunlight shines through dense treetops, casting dappled light, forming layers of light and shadow interweaving on the ground, as if painting a natural canvas. The air is filled with fresh breath, occasional bird calls are deep and solemn, adding a dignified atmosphere. The entire scene exudes a sense of grandeur and tranquility, inspiring reverence. This forest seems to be a witness to time, carrying countless stories and secrets, making people feel the dignity and mystery of nature, inspiring awe, as if standing in a spiritual place. |
7. Style
Type | Prompt Example |
Cyberpunk | Retro cyberpunk style - Under flickering neon lights, a cyber warrior in a leather jacket passes through an abandoned electronics factory, the camera pulls back from his back view to show a futuristic city night scene. |
Post-apocalyptic Style | The video shows a flying fairy from another world making a stunning appearance against a post-apocalyptic background. She wears tattered yet magnificent attire, with a pair of peculiar wings made of ruins fragments unfolding behind her, soaring over the desolate landscape. The camera follows her flight trajectory, rising from low altitude to the vast sky, showing her graceful figure in stark contrast to the post-apocalyptic world, each flap of her wings seeming to tell a story of survival and hope. |
Line Drawing Illustration | In court, a clever and eloquent fox lawyer, dressed in a neat lawyer's robe, is eloquently defending her client, each of her arguments is precise and powerful, moving all listeners, line drawing animation. |
Chinese Style Animation | Chinese animation style time-traveling girl, learning etiquette in an ancient palace under candlelight, every movement showing ancient elegance. |
Felt Style | The video shows a vivid scene of a character in a kitchen environment, especially unique because this character is made of felt, adding a touch of childlike fun. The felt little person is standing in a miniature kitchen, holding a small spatula, as if carefully cooking delicious food. The background is a wall hung with various kitchen utensils, the entire space filled with a warm atmosphere. The video captures every movement of the felt little person through a fixed perspective, including stirring, stir-frying, etc., showing its exquisite "culinary skills." |
Classic Masterpiece | In Van Gogh's "Starry Night," a skateboarding youth wearing modern clothing weaves through twisted trees, the light and shadow effects under the starry sky interplay with the trajectory of the skateboard. |
Pixel Game | A person stands in a game-style pixel world, equipped with the most gorgeous, high-resolution 8K texture pack. |
Conclusion on Video Content Creation
This article has provided a detailed guide on creating effective prompts for prompts for Wan2.1 text to video generation. We’ve explored four different prompt formulas, ranging from the Basic Formula suitable for beginners to the Transformation Formula designed for specific creative needs, each with its own applications and advantages.
The Prompt in different dimensions section offers a rich collection of reference examples covering seven dimensions: shot size, angle, lens types, camera movements, speed effects, atmosphere, and style. By skillfully utilizing prompts in these dimensions, we can more precisely control the visual effects of generated videos, enhancing their professional quality and storytelling capabilities.
By leveraging advanced video tools, creators can produce high-quality videos more efficiently and effectively. Ready to create your own AI-generated videos? Start using MimicPC’s ready-to-use Wan2.1 text to video workflow today, and remember to tailor your content to the appropriate target audience for maximum engagement and effectiveness.