How to Use FLUX 3 Max Text to Video in opencode
FLUX 3 Max Text to Video creates short scenes from descriptions of action, camera movement, lighting, and sound. Unlike FLUX 3 Max Image to Video, it needs no starting image, making it useful for exploring a written brief.
Prompts to try with FLUX 3 Max Text to Video in opencode
Copy an example into opencode, or ask in your own words.
Read the landing page brief in this project. Use FLUX 3 Max Text to Video to make a 5-second, 720p background shot of rain moving across a greenhouse roof, with a locked camera and audio disabled.
Read the game's station scene description. Use FLUX 3 Max Text to Video for a 10-second, 720p establishing shot: a train rolls into an empty platform at dawn, the camera holds still, and brakes hiss.
Use FLUX 3 Max Text to Video to create two 5-second, 720p shots for this project's coffee campaign. In one, hold the camera still as coffee pours; in the other, slowly move closer. Include pouring and café room sound.
Estimate, then generate a 5-second 9:16 clip with FLUX 3 Max Text to Video: a paper boat drifting down a rainy street. Save the result in ./assets.
Make a 10-second product teaser with FLUX 3 Max Text to Video for a smartwatch, slow orbit shot, studio lighting.
How to set up FLUX 3 Max Text 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 FLUX 3 Max Text 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": "blackforestlabs/flux-3-max/text-to-video", "input": { "prompt": "A red panda walks along a mossy log in a sunlit forest, pausing to sniff the air before climbing over a fallen branch. Soft morning light filters through the…" } }'
Then paste one of the prompts above: opencode finds FLUX 3 Max Text to Video on Spiral, shows the price and runs it.
FLUX 3 Max Text to Video providers and prices
Spiral runs FLUX 3 Max Text to Video through fal. Open a card for today's price, with every fee included.
$1.105 per run at the default inputs. resolution: 720p (default) $1.105, 1080p $1.885.
Settings you can ask for
FLUX 3 Max Text to Video works from your prompt. Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Duration | 5 to 20 | 5 | Duration of the generated video in seconds. |
| Resolution | 720p or 1080p | 720p | Resolution of the generated video. |
| Reasoning level | low or high | high | How much effort the harness spends reasoning about the given prompt. Higher reasoning effort means slower generation time. |
| Aspect ratio | auto, 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16 | auto | Aspect ratio of the generated video. |
| Generate audio | on or off | on | Whether to generate audio for the video. |
| Seed | a whole number | The seed to use for the generation. Random when not provided. |
Every API field of FLUX 3 Max Text to Video is on its tool page: open its card above.
What can you do with FLUX 3 Max Text to Video in opencode?
Turn a project's creative brief into short video assets with directed motion and sound. A coding agent can prepare shot descriptions from project files and place reviewed clips into the app or site.
Product scene concepts
Explore a short tabletop scene: a ceramic cup sits beside a pouring kettle as steam rises. Direct one camera move and the sound of pouring water.
Establishing shots
Create a brief opening view for a fictional location, such as a harbor at dawn with boats rocking and distant gulls.
Short narrative beats
Stage one story moment, such as a traveler entering a station and pausing beneath the departure board. Keep the action within a 5 to 20-second shot.
Camera movement studies
Compare a locked camera with a slow push toward the same subject. Use the clips to choose a visual direction before planning a shoot.
Atmosphere inserts
Make short inserts of rain, drifting steam, or wind moving fabric. Pair the visible movement with specific environmental sounds.
Dialogue scene tests
Try a brief exchange or a single spoken line before committing to a longer scene. Review the picture and generated speech together.
More on FLUX 3 Max Text to Video and opencode
Overview
FLUX 3 Max Text to Video in other agents
Questions about FLUX 3 Max Text to Video in opencode
Can opencode use FLUX 3 Max Text to Video?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run FLUX 3 Max Text to Video like any built-in tool.
How much does FLUX 3 Max Text to Video cost in opencode?
$1.105 per run at the default inputs. `resolution`: 720p (default) $1.105, 1080p $1.885. 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 FLUX 3 Max Text to Video in opencode?
No. Spiral runs FLUX 3 Max Text 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 FLUX 3 Max Text to Video in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while FLUX 3 Max Text to Video runs?
FLUX 3 Max Text to Video runs in the background. opencode starts the run, checks on it and gives you the video when it's ready.
What is FLUX 3 Max useful for?
Use it for short scenes with directed action, camera movement, lighting, and generated sound. Practical starting points include product scenes, establishing shots, and short story beats.
How long can a FLUX 3 Max video be?
Each generation lasts 5 to 20 seconds, in one-second increments. Plan a longer piece as separate shots to edit together.
Is FLUX 3 Max's 1080p output native?
The video is generated at 720p, then upscaled for 1080p delivery. Exact pixel dimensions depend on the chosen frame shape.
Can FLUX 3 Max make dialogue and sound effects?
Yes. Speech, effects, and environmental sound can be generated alongside the picture; describe the intended sound in your scene prompt.
How should I describe camera movement?
Name one movement and its speed, such as a slow push toward the subject. Start with that simple direction before adding more camera behavior.
Start using FLUX 3 Max Text 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


