How to Use Wan 2.2 A14B Video to Video in opencode
Rework existing footage using a written visual direction. Unlike Wan 2.2 A14B Image to Video, it starts from moving footage; transformation strength determines how far the result follows the new prompt.
Prompts to try with Wan 2.2 A14B Video to Video in opencode
Copy an example into opencode, or ask in your own words.
Use the sample footage in this project with Wan 2.2 A14B Video to Video to test a muted watercolor treatment. Start with transformation strength 0.35, generate at 720p, and place the original and result in a review page.
Estimate, then generate a 5-second 9:16 clip with Wan 2.2 A14B Video to Video: a paper boat drifting down a rainy street. Save the result in ./assets.
Make a 10-second product teaser with Wan 2.2 A14B Video to Video for a smartwatch, slow orbit shot, studio lighting.
Generate three 5-second b-roll clips of a busy coffee shop with Wan 2.2 A14B Video to Video and list what each cost.
Make a 6-second 16:9 drone shot over a misty pine forest at sunrise with Wan 2.2 A14B Video to Video.
How to set up Wan 2.2 A14B Video to Video in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run Wan 2.2 A14B Video to Video
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/wan/v2.2-a14b/video-to-video", "input": { "video_url": "https://storage.googleapis.com/falserverless/example_inputs/wan-2.2-v2v-input.mp4", "prompt": "A low-angle medium shot captures a domestic white cat with brown and black patches and a blue bandana sitting on a light-colored tiled floor indoors,…" } }'
Then paste one of the prompts above: opencode finds Wan 2.2 A14B Video to Video on Spiral, shows the price and runs it.
Wan 2.2 A14B Video to Video providers and prices
Spiral runs Wan 2.2 A14B Video to Video through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Wan 2.2 A14B Video to Video works from your video URL and prompt. Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Strength | 0 to 1 | 0.9 | Strength of the video transformation. A value of 1.0 means the output will be completely based on the prompt, while a value of 0.0 means the output will be identical to the input video. |
| Number of frames | 17 to 161 | 81 | Number of frames to generate. Must be between 17 to 161 (inclusive). |
| Frames per second | 4 to 60 | 16 | Frames per second of the generated video. Must be between 4 to 60. When using interpolation and |
| Negative prompt | what to leave out, in words | Negative prompt for video generation. | |
| Seed | a whole number | Random seed for reproducibility. If None, a random seed is chosen. | |
| Resolution | 480p, 580p, or 720p | 720p | Resolution of the generated video (480p, 580p, or 720p). |
| Aspect ratio | auto, 16:9, 9:16, or 1:1 | auto | Aspect ratio of the generated video. If 'auto', the aspect ratio will be determined automatically based on the input video. |
| Number of inference steps | 2 to 40 | 27 | Number of inference steps for sampling. Higher values give better quality but take longer. |
| Enable prompt expansion | on or off | off | Whether to enable prompt expansion. This will use a large language model to expand the prompt with additional details while maintaining the original meaning. |
| Acceleration | none or regular | regular | Acceleration level to use. The more acceleration, the faster the generation, but with lower quality. The recommended value is 'regular'. |
| Guidance scale (1st stage) | 1 to 10 | 3.5 | Classifier-free guidance scale. Higher values give better adherence to the prompt but may decrease quality. |
| Guidance scale (2nd stage) | 1 to 10 | 4 | Guidance scale for the second stage of the model. This is used to control the adherence to the prompt in the second stage of the model. |
| Shift | 1 to 10 | 5 | Shift value for the video. Must be between 1.0 and 10.0. |
| Interpolator model | none, film, or rife | film | The model to use for frame interpolation. If None, no interpolation is applied. |
| Number of interpolated frames | 0 to 4 | 1 | Number of frames to interpolate between each pair of generated frames. Must be between 0 and 4. |
| Adjust FPS for interpolation | on or off | on | If true, the number of frames per second will be multiplied by the number of interpolated frames plus one. For example, if the generated frames per second is 16 and the number of interpolated frames is 1, the final frames per second will be 32. If false, the passed frames per second will be used as-is. |
| Video quality | low, medium, high, or maximum | high | The quality of the output video. Higher quality means better visual quality but larger file size. |
| Video write mode | fast, balanced, or small | balanced | The write mode of the output video. Faster write mode means faster results but larger file size, balanced write mode is a good compromise between speed and quality, and small write mode is the slowest but produces the smallest file size. |
| Resample video frame rate | on or off | off | If true, the video will be resampled to the passed frames per second. If false, the video will not be resampled. |
Every API field of Wan · Video to Video is on its tool page: open its card above.
What can you do with Wan 2.2 A14B Video to Video in opencode?
Create cinematic assets for a project directly from its creative brief. A coding agent can turn the brief into shot prompts, organize candidate clips, and prepare the selected take for the interface.
Advertising shot concepts
Draft a product-focused shot with deliberate framing, a clear action, and a specified light source. Compare the visual direction before committing to a full production.
Film shot previsualization
Test how a single story beat reads with a particular camera angle, movement, and color palette. Use the result to discuss the shot with an editor or director.
Atmospheric inserts
Create short inserts such as drifting fog, rain on a window, or wind moving through grass. Specify restrained motion and a fixed camera when the environment should carry the shot.
Lighting and color studies
Explore a scene under warm window light, cool overcast light, or hard side lighting. Change one visual instruction per take to make the comparison useful.
Footage restyling tests
Use existing footage to explore a different visual treatment, such as a muted painted look. Start with a restrained transformation and increase it only if the change is too subtle.
More on Wan 2.2 A14B Video to Video and opencode
Overview
Wan 2.2 A14B Video to Video in other agents
Questions about Wan 2.2 A14B Video to Video in opencode
Can opencode use Wan 2.2 A14B Video to Video?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Wan 2.2 A14B Video to Video like any built-in tool.
How much does Wan 2.2 A14B Video to Video cost in opencode?
Up to $6.24 per run at the default inputs for 60 seconds of input. `resolution`: 480p $3.12, 580p $4.68, 720p (default) $6.24. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your opencode plan is separate.
Do I need a fal account to use Wan 2.2 A14B Video to Video in opencode?
No. Spiral runs Wan 2.2 A14B Video to Video on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up Wan 2.2 A14B Video to Video in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while Wan 2.2 A14B Video to Video runs?
Wan 2.2 A14B Video to Video runs in the background. opencode starts the run, checks on it and gives you the video when it's ready.
What is Wan 2.2 A14B useful for?
Use it for short visual shots where lighting, composition, and color matter: advertising concepts, atmospheric inserts, and film previsualization. Give those choices explicitly in the prompt.
How should I write a Wan 2.2 prompt?
Describe the subject, setting, and action, then add the framing, camera movement, and lighting. For a first test, keep the request to one clear shot.
Can Wan 2.2 A14B generate native 4K video?
These models output up to 720p. Writing “4K” in the prompt does not change that ceiling; upscale the finished clip separately if you need a larger deliverable.
Does Wan 2.2 A14B generate sound or spoken dialogue?
Plan to add dialogue, music, and sound effects separately. Native synchronized audio arrived with Wan 2.5.
When should I use prompt expansion?
Try it when your description is brief and you want additional visual detail. Leave it off when testing an exact shot description so you can judge your wording directly.
Start using Wan 2.2 A14B Video to Video in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


