Wan 2.6 Flash Prompts: 4 Templates with Real Clips

TL;DR

• 4 ready-to-use scenes: an animal close-up, a vertical night market (with audio), a 1080p product orbit, and a 10-second rainy push-in — all real wan2.6-flash/image-to-video clips; the default tier runs $0.145 for 5 seconds (full pricing on the pricing page).
• Each scene lists the input image, the prompt, and a pre-fill link; the aspect follows the input image. Code lives in the API guide.
• New accounts get 200 credits; $10 buys about 68 clips at the default tier.

Scene 1: Animal close-up (default tier, silent)

·

Watch the full clip →

The fox turns its head toward the camera, its ears twitch, golden leaves drift down through the misty light

Try this prompt →

wan2.6-flash/image-to-video, 720p, 5 s, 16:9, 1280×720, silent, $0.145.

How to write it: small actions (the turn, the ear twitch) plus ambient motion (drifting leaves); the subject and light belong to the photo.

Scene 2: Vertical night market (audio on)

·

Watch the full clip →

The vendor tosses the noodles in the wok, flames flare up, steam billows, the crowd chatters in the background

Try this prompt →

wan2.6-flash/image-to-video, 720P · Sound On, 5 s, 9:16 (portrait in, portrait out), 720×1280, $0.2875.

How to write it: put the ambient sound in the prompt (the chattering crowd) and set audio: true — the wok, flames, and crowd arrive with the picture; a portrait input gives 9:16 with no cropping.

Scene 3: Product orbit (1080p)

·

Watch the full clip →

The camera slowly dollies around the turquoise convertible as the sun sinks behind the mesas, dust drifting in the warm light

Try this prompt →

wan2.6-flash/image-to-video, 1080P, 5 s, 16:9, 1918×1080, silent, $0.215.

How to write it: use the product shot as input and write the rig (dollies around) plus a light change (sunset, dust); finish at 1080p so the detail survives zooming.

Scene 4: 10-second rainy push-in (3:4 follows the photo)

·

Watch the full clip →

She tilts the umbrella and looks up at the rain, raindrops run down the clear canopy, city lights shimmer in the puddles, the camera slowly pushes in

Try this prompt →

wan2.6-flash/image-to-video, 720p, 10 s, 3:4, 830×1108, silent, $0.29.

How to write it: chain the action sequence (tilt → look up → droplets → push-in); ten seconds holds the whole move, and a 3:4 photo yields a 3:4 clip.

How to write these prompts (3 lines)

1. Write only motion, camera, and mood; the input image owns the subject. Chinese or English, up to 1,500 characters.
2. Name the rig concretely: dollies around, pushes in beats "cinematic."
3. Match duration to the action: one move fits 5 seconds; a sequence needs 10 or 15.

FAQ

Does the aspect follow the input image?

Yes. Portrait in gives vertical, 3:4 gives 3:4 — no parameter.

How do I turn on audio?

Pass audio: true explicitly; it bills at the Sound On rate (about 2×).

Do Chinese prompts work?

Yes, the model takes both languages.

Next: pick one of your images, follow the link to pre-fill a prompt, and run a 5-second default-tier take.