How to Use LongCat Video Text to Video 720p in opencode
Create 720p footage from text when you want to specify the scene, action, and camera direction yourself. Compared with LongCat Video Text to Video 480p, it adds refinement for higher-resolution output.
Prompts to try with LongCat Video Text to Video 720p in opencode
Copy an example into opencode, or ask in your own words.
Read the storyboard notes and use LongCat Video Text to Video 720p for the opening location. Show a quiet train platform at dawn with a slow camera pan and pale natural light; keep people out of the shot.
Use LongCat Video Text to Video 720p to animate the product photo in the project's assets. Request a gentle forward camera move while the product stays still, then flag visible changes to its shape or surface details.
Estimate, then generate a 5-second 9:16 clip with LongCat Video Text to Video 720p: a paper boat drifting down a rainy street. Save the result in ./assets.
Make a 10-second product teaser with LongCat Video Text to Video 720p for a smartwatch, slow orbit shot, studio lighting.
Generate three 5-second b-roll clips of a busy coffee shop with LongCat Video Text to Video 720p and list what each cost.
How to set up LongCat Video Text to Video 720p 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 LongCat Video Text to Video 720p
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/longcat-video/text-to-video/720p", "input": { "prompt": "realistic filming style, a person wearing a dark helmet, a deep-colored jacket, blue jeans, and bright yellow shoes rides a skateboard along a winding mountain…" } }'
Then paste one of the prompts above: opencode finds LongCat Video Text to Video 720p on Spiral, shows the price and runs it.
LongCat Video Text to Video 720p providers and prices
Spiral runs LongCat Video Text to Video 720p through fal. Open a card for today's price, with every fee included.
$0.052 per 30 seconds. Billed on num_frames, default 162, rounded up to the next 30 seconds.
Settings you can ask for
LongCat Video Text to Video 720p works from your prompt. Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Negative prompt | what to leave out, in words | Bright tones, overexposed, static, blurred details, subtitles, style, works, paintings, images, static, overall gray, worst quality, low quality, JPEG compression residue, ugly, incomplete, extra fingers, poorly drawn hands, poorly drawn faces, deformed, disfigured, misshapen limbs, fused fingers, still picture, messy background, three legs, many people in the background, walking backwards | The negative prompt to use for the video generation. |
| Number of frames | 17 to 961 | 162 | The number of frames to generate. |
| Number of inference steps | 8 to 50 | 40 | The number of inference steps to use for the video generation. |
| Number of refinement inference steps | 8 to 50 | 40 | The number of inference steps to use for refinement. |
| Guidance scale | 1 to 10 | 4 | The guidance scale to use for the video generation. |
| Aspect ratio | 16:9, 9:16, or 1:1 | 16:9 | The aspect ratio of the generated video. |
| FPS | 1 to 60 | 30 | The frame rate of the generated video. |
| Seed | a whole number | The seed for the random number generator. | |
| Enable prompt expansion | on or off | off | Whether to enable prompt expansion. |
| Video output type | X264 (.mp4), VP9 (.webm), PRORES4444 (.mov), or GIF (.gif) | X264 (.mp4) | The output type of the generated video. |
| Video quality | low, medium, high, or maximum | high | The quality of the generated video. |
| Video write mode | fast, balanced, or small | balanced | The write mode of the generated video. |
| Acceleration | none or regular | regular | The acceleration level to use for the video generation. |
Every API field of LongCat Video 720p · Text to Video is on its tool page: open its card above.
What can you do with LongCat Video Text to Video 720p in opencode?
Turn a project's visual brief into motion drafts for storyboards, backgrounds, or illustrative scenes. Have the agent translate design notes into a subject, action, camera direction, and style, then review the result against that brief.
Storyboard motion studies
Test a single action and camera direction before committing to a shot: a person turns toward a window while the camera slowly moves closer.
Landscape establishing shots
Create illustrative footage of mist crossing a hillside, wind moving through grass, or a camera panning across a mountain valley.
Visual style comparisons
Explore the same simple action in different treatments, such as realistic photography and watercolor animation. Keep the action and framing consistent when comparing results.
Camera direction tests
Compare a fixed view, a slow pan, and a gentle forward move for the same scene. Use the results to choose a camera direction for an edit.
Imagined locations
Describe a location that has no reference image, such as a greenhouse on a snowy rooftop. Use one camera move to explore its layout and atmosphere.
Script scene previews
Turn a short written scene into a visual draft. Specify the subject, one action, lighting, and framing, then review whether the intended event reads clearly.
More on LongCat Video Text to Video 720p and opencode
Overview
LongCat Video Text to Video 720p in other agents
Questions about LongCat Video Text to Video 720p in opencode
Can opencode use LongCat Video Text to Video 720p?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run LongCat Video Text to Video 720p like any built-in tool.
How much does LongCat Video Text to Video 720p cost in opencode?
$0.052 per 30 seconds. Billed on `num_frames`, default 162. 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 LongCat Video Text to Video 720p in opencode?
No. Spiral runs LongCat Video Text to Video 720p on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up LongCat Video Text to Video 720p in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while LongCat Video Text to Video 720p runs?
LongCat Video Text to Video 720p runs in the background. opencode starts the run, checks on it and gives you the video when it's ready.
What is LongCat Video useful for?
Use it to explore camera movement, action, and visual style in storyboard shots or illustrative footage. Camera motion and visual style received targeted training.
What is the difference between 480p and 720p?
The 720p versions add refinement for higher-resolution output. The maker reports that this process improves texture detail and can correct local distortions.
Can I prompt LongCat Video in Chinese?
Yes. LongCat Video supports English and Chinese prompts.
How should I describe camera movement?
Give a concrete direction such as a slow pan, a forward camera move, or a fixed close-up. Describe the subject's action separately so you can judge whether both instructions appear in the result.
What should I check before using a clip?
Check whether the action follows your description and remains consistent throughout the shot. The maker's tests identify motion, prompt alignment, and preservation of a starting image as areas that can need improvement.
Start using LongCat Video Text to Video 720p 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


