Keywords

How to use keywords in Qolaba's Video Generation workspace

Keywords are structured input controls that extend and refine what your prompt describes. Where a prompt sets the scene in natural language, keywords give you precise, reliable control over motion style, camera behavior, visual quality, lighting, and focus — with consistent results across generations.

---

How Keywords Work

Keywords are selected from categorized panels in the Input Controls area. When added to a generation, they are appended to your prompt as structured directives that influence how the model interprets and generates the video. Multiple keywords from different categories can be combined in a single generation.

Think of keywords as precision tools. Your prompt sets the creative direction — keywords fine-tune the technical and stylistic execution.

---

Motion Keywords

Motion keywords control how subjects and the camera move within the scene.

Keyword	Effect
Static	No camera movement — fixed, stable shot
Move Left	Camera or subject moves left
Move Right	Camera or subject moves right
Move Up	Camera or subject moves upward
Move Down	Camera or subject moves downward
Zoom In	Camera closes in on the subject
Zoom Out	Camera pulls back from the subject
Pan Right	Camera rotates horizontally to the right
Pan Left	Camera rotates horizontally to the left

Combine motion keywords with camera movement descriptors in your prompt for the most controlled output — e.g., Zoom In keyword + "slow dolly forward" in the prompt.

---

Focus Keywords

Focus keywords control depth of field and shot framing.

Keyword	Effect
Shallow Depth of Field	Background blurred, subject sharp — isolates the subject
Bokeh	Soft, circular background blur — cinematic and aesthetic
Close-Up Shot	Tight framing on subject detail
Short Shot	Slightly wider than close-up — head and shoulders framing
Medium Wide Shot	Subject visible from waist up with environment context
Extreme Wide Shot	Subject small within a large environment — establishes scale

---

Lens Keywords

Lens keywords simulate different camera lens types and their visual characteristics.

Keyword	Effect
Macro Lens	Extreme close-up detail — ideal for small subjects or textures
Zoom Lens	Optical zoom effect with perspective compression
Infrared Lens	Infrared color effect — surreal, high-contrast aesthetic

---

Enhancement Keywords

Enhancement keywords improve overall visual quality and add cinematic polish to the output.

Keyword	Effect
Cinematic	Adds filmic quality, widescreen feel, and dramatic pacing
4K	Signals high-resolution, highly detailed output
Sharp Focus	Ensures subject clarity and crisp edges
Photorealistic	Pushes the model toward real-world visual accuracy
Highly Detailed	Increases surface texture and environmental detail
Photo Shoot	Clean, well-lit, professionally framed aesthetic

---

Lighting Keywords

Lighting keywords define how the scene is lit — affecting mood, contrast, and visual tone.

Keyword	Effect
Hard Lighting	High contrast, defined shadows — dramatic and intense
Soft Lighting	Diffused, gentle light — flattering and natural
Key Lighting	Single dominant light source — studio or portrait look
Golden Hour	Warm, orange-tinted natural light — sunrise or sunset feel
Neon Lighting	Vivid artificial colored light — urban and cyberpunk aesthetic
Backlit	Light source behind the subject — silhouette or halo effect

---

Landscape & Environment Keywords

Environment keywords set the broader atmospheric and geographical context of the scene.

Keyword	Effect
Sunrise	Early morning warm light and atmosphere
Stream Landscape	Flowing water in a natural setting
Urban Environment	City streets, buildings, and infrastructure
Forest	Dense natural tree cover and foliage
Desert	Arid, sandy or rocky open landscape
Ocean	Open water, waves, coastal setting

---

Negative Keywords

Negative keywords tell the model what to exclude from the generation. They are as important as positive keywords for controlling output quality and eliminating unwanted elements.

Common negative keywords to use:

Negative Keyword	What It Removes
Blur	Reduces unwanted motion blur or soft focus
Low quality	Discourages pixelated or low-fidelity output
Distortion	Reduces warping or unnatural deformation
Watermark	Removes visible watermarks or text overlays
Extra limbs	Reduces anatomical errors in human subjects
Duplicate subjects	Prevents unwanted subject repetition
Text	Removes generated text from the video

Always include negative keywords when generating human subjects — extra limbs, distortion, and duplicate subjects significantly reduce common anatomical errors in AI video.

---

Combining Keywords Effectively

Keywords are most powerful when used in coordinated combinations. Here are recommended sets by use case:

1. Cinematic product showcase: Cinematic + Shallow Depth of Field + Key Lighting + Sharp Focus + 4K

2. Social media lifestyle clip: Move Right + Golden Hour + Bokeh + Highly Detailed + Photorealistic

3. Dramatic landscape reveal: Zoom Out + Extreme Wide Shot + Cinematic + Hard Lighting + 4K

4. Close-up texture or detail shot: Macro Lens + Sharp Focus + Soft Lighting + Highly Detailed + Static

5. Urban night scene: Neon Lighting + Cinematic + Pan Right + Shallow Depth of Field + Highly Detailed