Summon

Summon is the animation module. It takes a text description or a still image and generates an animated video — motion graphics, animated scenes, kinetic text, visual effects. Everything renders locally on your machine, so there are no upload limits and no cloud fees per render.

Describe the animation you want in plain text. The more specific you are about motion, the better the result:

· "Logo on black background, gold particles floating upward, slow fade in"

· "Abstract geometric shapes rotating, loop-ready, minimal color palette"

· "Text appearing letter by letter with a soft glow, centered on screen"

For batch generation, enter one prompt per line. Summon works through all of them in sequence — useful for generating a full set of motion graphic variations at once.

Drop one or more images from your Evoke output or any folder. Summon analyzes each image as a cinematic video frame — reading the composition, mood, subject, and visual style — and generates an animation that matches it naturally.

Images are processed one at a time and results appear as each one finishes. You can keep adding images while earlier ones are still processing.

Once you're happy with a preview, set your render settings:

· FPS: 24 for a cinematic feel, 30 for motion graphics and social content

· Duration: typically 5–15 seconds for stock

· Resolution: 1080p for standard, 4K if your machine can handle it

· Format: MP4 for uploads, ProRes for masters

Click Render and the animation exports locally. Results stack in the panel — use Clear Results to reset when you're done with a batch.

Queue multiple animations and render them unattended. Each item in the queue shows its own progress. Leave it running overnight and come back to a full set of finished video files.

Generated animations accumulate in the results panel — they don't clear when you switch modes or start a new batch, so you can freely mix prompt and image results in one session.