Today we will explore how to utilizeMidjourneyGenerate high-quality novel tie-ins, especially for audiobook tie-in needs.
We will learn how to make our work stand out in a crowd of homogenized products through carefully constructed cue words.
I. From business needs
We were faced with a business need to produce an audiobook of a novel, The Girl Who Survived in the Snowy Mountains, with accompanying graphics. Our goal was to use Midjourney to generate movie-quality graphics that would make this work stand out in the marketplace.
II. Construction of cue words
1、Body and details
First, we need to clarify the subject and details of the picture. Take "Girl Surviving in the Snowy Mountains" as an example, the subject is the girl, and the details include her appearance, clothes and environment. For example, we can describe her as "a Chinese girl, wearing a thick gray and white cotton jacket, with long hair".
2. Environmental context
Next, we need to build the environmental background, including the environment, light, color and atmosphere. The environment background is the main tone of the picture and determines the overall style of the picture. For example, our environment is snowy mountains, the light is cinematic light effects, the color is cold tones, and the atmosphere is the tension of survival.
3. Perspective and Scenery
Viewpoint and composition determine the visual effect of the picture. We can choose different viewpoints (e.g. bird's eye view, side view, etc.) and views (e.g. panorama, close-up, etc.) to enrich the picture. For example, we can choose to shoot from the back to show the contrast between the girl and the snow-covered mountain in a panoramic view.
4. Artistic style and production method
Art style and production method are the key to the effect of the picture. We can choose different art styles (e.g. Zhang Yimou style, Wong Kar Wai style, etc.) and production methods (e.g. oil painting, 3D rendering, etc.) to create unique visual effects.
5. Quality of work
We can improve the overall quality of the image by adding some of the catch-all words that improve the quality of a photo (e.g. CG, 8K, HDR, etc.).
III. Use of cue word symbols
1. Semantic compartmentalization symbols
When we need Midjourney to understand two different concepts, we can use two colons for semantic separation. For example, to avoid "hot dog" being misunderstood as a hot dog, we can write "hot:: dog" to express a very hot dog.
2. Weighted Emphasis Symbols
The weighted emphasis symbol "two colons + number" can increase the proportion or importance of a particular element in a picture. For example, "1boy::2,1girl::1" would make the boy take up a larger portion of the picture.
Fourth, AI-assisted generation of prompt words
Midjourney not only generates images, but also helps us generate descriptors. All we need to do is provide a topic and Midjourney will generate a series of related descriptors, greatly simplifying our workflow.
Now that you are a cue word generator based on input descriptions, you will generate cue words by visualizing the natural language I input as a complete picture. Please note that your generated content serves a drawing AI, which can only understand figurative cues and not abstract concepts. I will provide a short description in Chinese, the generator needs to provide me with the exact cue words, optimize and reorganize as necessary to provide more accurate content, and also output only the translated English content.
Please mimic the structure of the example to generate the perfect prompt words.
Example input: "A female office worker sitting on the curb"
Example output: 1 girl, office lady, solo, 16yo,beautiful detailed eyes, light blush, black hair, long hair, mole under eye, nose blush , looking at viewer, suits, white shirt, striped miniskirt, lace black pantyhose, black heels, LV bags, thighhighs,sitting, street, shop border, akihabara , tokyo, tree, rain cloudy, beautifully detailed background, depth of field, loli, realistic, ambient light, cinematic composition, neon lights, HDR, Accent Lighting, pantyshot, fish eye lens, black lace black pantyhose pantyshot, fish eye lens.
Please read my requirements carefully and follow the rules strictly to generate prompt words, if you understand, please reply "I am ready", when I enter the Chinese content, please generate the English content I need. Note that the English words are written consecutively without serial numbers.
V. Conclusion
In this section, we have learned how to build high-quality cues and how to utilize AI to assist in generating cues.
In the next section, we'll continue to dive into other advanced features of Midjourney.
