AI prompt library with real image and video examples.

Explore verified prompts for Seedance 2.5, GPT Image 2, MiniMax H3, and more. Filter by generation type and use case, then continue in the matching Playground.

Seedance series

23 prompts found

All prompts
2026-09-24

Tokyo Twilight Slow Living

A young woman cycles, sketches, and wanders through quiet Tokyo neighborhoods in a reflective twilight slow-living film.

seedance-2-0VideoShort drama
2026-09-24

Cliffside Piano Rhapsody

A pianist performs on a mountaintop cliff in a continuous cinematic shot that moves from sweeping landscape to tactile keyboard detail.

seedance-2-0VideoShort dramaBrand marketing
2026-09-24

Chubby Cat Snowboard Champion

A photoreal chubby cat performs a big-air snowboard run under stadium lights with breath vapor, crowd scale, and convincing snow physics.

seedance-2-0VideoShort dramaBrand marketing
2026-09-24

Elven Queen at Twilight

An elven queen surveys a luminous forest at twilight as bioluminescent flowers and fireflies shape a graceful fantasy portrait.

seedance-2-0VideoShort drama
2026-09-24

Golden Morning Rituals

A consistent protagonist moves through a calm morning routine, exercise, balcony gardening, and warm natural light.

seedance-2-0VideoShort drama
2026-09-24

Miniature Bakery World

Tiny chefs work continuously around a towering pancake stack as honey, berries, and powdered sugar animate a miniature bakery world.

seedance-2-0VideoShort dramaBrand marketing
2026-09-24

Paris Haute Couture Show

A Paris couture runway uses focused spotlights, rich fabric motion, and polished reflections for a premium fashion-film finish.

seedance-2-0VideoShort drama
2026-09-24

Kitchen Rush in 8K

A single impossible camera move races through a high-end commercial kitchen as chefs, ingredients, and stainless-steel stations surge through dinner service.

seedance-2-0VideoShort drama

AI prompt library FAQ

Are these AI image and video prompts free to use?

Yes. You can browse and copy every prompt for free. Generating a new result in Playground is billed at the current price of the model you select.

How do I write a Seedance 2.5 or MiniMax H3 video prompt?

Describe the subject and action first, then the scene, shot sequence, camera movement, timing, sound, and anything that must remain unchanged. Use a clear chronological order instead of a list of vague style words.

What is the difference between text-to-video, image-to-video, and multimodal-reference prompts?

Text-to-video defines the whole scene in words. Image-to-video focuses on motion and camera changes while preserving the source image. Multimodal-reference prompts assign a specific role to each image, video, or audio reference.

How do I write a good GPT Image 2 prompt?

Specify the subject, composition, camera angle, lighting, materials or visual style, required text and layout, then add constraints such as no logos, watermarks, or distorted hands.

Can I copy a prompt directly into Flatkey Playground?

Yes. Open any example to load its prompt, model, and output into the matching Playground, where you can edit variables and generate your own version.

Why do examples show the prompt, model, and real output together?

The output lets you judge whether the prompt structure and model fit your goal before spending time or credits on a new generation.

Free prompt library

Pick a prompt and generate it.

Open a verified image or video prompt in the matching Flatkey Playground, then adjust the model and settings for your own result.