AI Image Generation

StarZero Agents can generate images from text descriptions using AI. Describe what you want — a product shot, an illustration, a stylized background — and StarZero Agents will create it. Generated images can be used as clips on your timeline, as reference material for video generation, or anywhere you need a custom visual.

Generating an Image

Describe what you want in the chat:

"Generate an image of a cozy coffee shop interior with warm lighting"

"Create a product photo of a sleek smartwatch on a marble surface"

"Make a stylized illustration of a mountain landscape at sunset in a flat design style"

StarZero Agents generates the image and displays it directly in the chat. You'll see a preview with a few handy controls:

• Click the image to open it in a full-size lightbox view
• Copy URL — Copy a direct link to the image for sharing or reuse
• Download — Save the image file to your computer

Tips for Good Prompts

Be specific about what you're looking for. The more detail you provide, the better the result:

• Subject — What's in the image? Be precise: "a golden retriever puppy sitting on grass" beats "a dog"
• Style — "photorealistic", "watercolor", "flat illustration", "cinematic", "vintage film"
• Composition — "close-up", "wide shot", "overhead view", "portrait orientation"
• Colors and lighting — "warm golden hour lighting", "neon-lit", "high contrast black and white"
• Mood — "serene and peaceful", "dramatic and intense", "playful and colorful"

Choosing an Aspect Ratio

You can request a specific aspect ratio to match your project format:

"Generate a 16:9 banner image of a sunset over the ocean"

"Create a 9:16 vertical image for a TikTok thumbnail"

"Make a square 1:1 image of a minimalist logo"

Supported aspect ratios include 1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, and more.

Using References

You can provide up to 10 references — images or short video clips — to guide the generation. References help the AI match a specific style, subject, or composition:

"Generate an image in the same style as this reference"

"Create a new product shot that matches the lighting from this photo"

"Use these three images as style references for a new illustration"

"Generate a poster inspired by the opening of this video clip"

References can come from:

• Your content library — video clips or extracted frames from your content
• Previously generated images or videos — refine by building on earlier results
• Rendered videos — use a rendered video from your project
• Pasted images — copy an image from any app and paste it directly into the chat input

For video references, you can specify a time range (up to 10 seconds) so the AI focuses on a particular moment. Image references ignore time ranges.

When providing multiple references, the AI considers them in order — you can refer to them as "the first reference", "the second reference", etc. Be explicit about what each reference contributes and what should appear in the result (e.g., "use the colors from the first reference and the composition from the second").

Editing and Iterating

If the generated image isn't quite right, ask StarZero Agents to modify it. When refining, be direct about what to change rather than re-describing the entire image:

"Make the sky more orange"

"Remove the text in the background"

"Move the subject slightly to the left"

StarZero Agents will use the previous image as a reference and apply your changes. This iterative approach lets you dial in exactly the look you want without starting from scratch each time.

Using Generated Images in Your Project

Generated images become regular image clips you can use in your video project:

"Add that generated image to the timeline for 4 seconds"

"Use that image as an overlay in the top right corner"

You can also use generated images as first frames for AI video generation, creating a seamless workflow from still image to animated video.

Credit Cost

Image generation costs credits based on the complexity of the generation. StarZero Agents will ask for your approval before generating, so you'll always know the cost upfront.

Compositing Text and Graphics onto Photos

You can use image generation to layer text, graphics, or design elements onto real photos or video frames. This is especially useful for creating thumbnails, posters, and promotional images that combine your actual footage with designed elements.

"Take a frame from the interview at 1:23 and add a bold title overlay that says 'The Future of AI'"

"Create a YouTube thumbnail using this frame with large text and a dramatic color treatment"

"Generate a poster-style image based on this clip with the show title and guest name"

To do this, provide a frame from your video (extracted or previously generated) as a reference image, and describe the text, graphics, or design treatment you want added. The AI composites everything into a single finished image.

Great Uses for Generated Images

• Thumbnails — Create eye-catching thumbnails by compositing text and graphics onto video frames
• Title cards — Generate custom backgrounds for title sequences
• B-roll — Fill gaps in your footage with generated visuals
• Storyboarding — Quickly visualize scenes before shooting
• Social media assets — Create matching images for video posts
• Posters — Combine photos with text and design elements for promotional graphics
• Reference frames — Generate a starting frame for AI video generation