> For the complete documentation index, see [llms.txt](https://docs.qolaba.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.qolaba.ai/video-generation/input-controls/prompt-and-magic-prompt.md). # Prompt and Magic Prompt The prompt is the primary input for every video generation. It tells the model what to generate — the subject, environment, action, camera movement, and mood. How you write it directly determines the quality and accuracy of the output. *** #### Writing an Effective Prompt A strong video prompt covers four elements: | Element | What to Include | | ------------------- | ----------------------------------------------------------- | | **Subject** | What or who is in the scene | | **Environment** | Where the scene takes place — setting, time of day, weather | | **Action & Motion** | What is happening — movement of subject and camera | | **Style & Mood** | Visual tone, aesthetic, and feeling | **Weak prompt:** ``` A person walking in a city. ``` **Strong prompt:** ``` A young woman in a long coat walking slowly through a rain-soaked city street at night, neon signs reflecting on wet pavement, slow tracking shot following from behind, cinematic and moody. ``` The second prompt gives the model a subject, environment, motion direction, camera movement, and visual mood — producing a far more consistent and usable output. *** #### Prompt Structure Guide **1. Lead with your subject** Start with who or what is the focus of the scene. ``` A lone astronaut standing on the surface of Mars... ``` **2. Describe the environment** Add setting, time, weather, and atmosphere. ``` ...surrounded by vast red desert plains under a pale orange sky at dusk... ``` **3. Define the motion** Specify both subject movement and camera movement. ``` ...slowly turning to look at the horizon, camera pulling back in a wide arc... ``` **4. Set the style and mood** Add visual tone, aesthetic references, and quality descriptors. ``` ...cinematic, photorealistic, sharp focus, golden hour lighting. ``` **Full combined prompt:** ``` A lone astronaut standing on the surface of Mars, surrounded by vast red desert plains under a pale orange sky at dusk, slowly turning to look at the horizon, camera pulling back in a wide arc, cinematic, photorealistic, sharp focus, golden hour lighting. ``` *** #### What to Avoid * **Vague descriptors** — "dramatic and cinematic" is less effective than "slow dolly forward through a foggy forest at dawn" * **Overloading with multiple scenes** — Keep each prompt focused on a single scene or moment * **Conflicting instructions** — Avoid combining contradictory motion directions (e.g., zoom in and pull back simultaneously) * **Describing abstract concepts without visual grounding** — "a feeling of loneliness" needs a concrete visual anchor to be generatable *** #### Magic Prompt Magic Prompt is an AI-powered enhancement tool that takes your prompt and rewrites it into a more detailed, generation-optimized version — automatically adding descriptive language, cinematic direction, and stylistic detail that improves output quality. **When to Use It** Use Magic Prompt when: * Your prompt is short or underdeveloped * You are not sure how to describe camera movement or visual style * You want to quickly explore an enhanced version of a simple idea * You are new to video prompting and want a better starting point **When to Skip It** Skip Magic Prompt when: * Your prompt is already highly specific and detailed * You are working with reference images where strict visual consistency matters * You need precise control over exactly what the model generates **How to Use It** 1. Enter your base prompt in the prompt input field 2. Click the **Magic Prompt** button 3. Qolaba rewrites and enhances your prompt automatically 4. Review the enhanced version — edit if needed before generating **Before Magic Prompt:** ``` A dog running on a beach. ``` **After Magic Prompt:** ``` A golden retriever running joyfully along a sun-drenched sandy beach, waves crashing gently in the background, slow-motion tracking shot from the side, warm afternoon light, shallow depth of field, cinematic and vibrant. ``` {% hint style="info" %} Use Magic Prompt as a starting point, not a final step. Always review the enhanced prompt and adjust anything that doesn't match your intent before generating. {% endhint %} --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.qolaba.ai/video-generation/input-controls/prompt-and-magic-prompt.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.