Skip to content

Wan 2.2 / Text to video

Wan 2.2 landscape prompts for water, clouds and atmosphere

A landscape clip can feel alive through small environmental motion. Water, clouds or foliage can carry the shot while the camera remains steady. This is a useful approach for B-roll and backgrounds where subject deformation would be distracting.

By JollyAIReviewed 2 min read

Choose one dominant movement

A waterfall already provides motion; it may not need a fast aerial camera move as well. A misty valley can use drifting cloud while the horizon remains fixed. Describe the direction and pace of the main effect instead of requesting several unrelated weather changes.

If the scene represents a real place, label a generated interpretation appropriately. Do not use invented landscape footage as evidence of actual weather, construction or environmental conditions.

Build the shot

  1. Select Wan Text to Video and choose the intended composition.
  2. Define foreground, landmark and background in a few clear sentences.
  3. Add one environmental movement and a restrained camera instruction.
  4. Review the horizon, repeated textures and continuity of the moving material.

Example prompt

PROMPT RECIPE / ADAPT TO YOUR SOURCE

A fictional mountain lake at early morning, dark rocks in the foreground and a distant ridge reflected in the water. Thin mist drifts slowly across the surface. The camera remains locked and the horizon stays level. Gentle ripples, soft natural light, one continuous landscape shot.

Make it useful in an edit

Find a stable interval with no sudden change in the terrain or lighting. Add ambience separately if the workflow output is silent. For a website background, keep the motion subdued and test a responsive crop. For narrated video, ensure the scenery supports the point being made rather than filling time with unrelated attractive footage.

REVIEWED JOLLYAI IMPLEMENTATION

The workflow behind the guide

Written scene → configured Wan text conditioning and sampling → frame decoding → video encoding and any selected post-processing.

Inputs, presets & access
PRO for the reviewed standard Wan T2V route. Use the visible preset; do not infer file metadata from the prompt.
Implementation note
JollyAI runs configured Wan workflows with locally selected checkpoints and adapters. T2V, I2V and first/last-frame are separate routes. Presets and post-processing differ by route. Plan sound separately for the demonstrated silent workflow, and inspect the downloaded file before quoting dimensions or duration.

Configuration reviewed September 20, 2026. Your current playground controls and plans page determine availability. Prompt recipes above are suggestions, not guarantees or claimed test results.

Open Text to video ↗

Sources and useful next steps

The implementation notes describe JollyAI's reviewed local integration. Upstream capabilities and licences may differ from the settings available here.

Found an outdated setting or a reproducible problem? Contact JollyAI with the workflow and job reference. Keep account tokens and private input files out of public reports.

KEEP BUILDING

Continue the workflow.