JavaScript guide
Generate comics with server-side JavaScript.
Use the native fetch API to create a generation, retain its ID, and poll the status endpoint until the job reaches a terminal state.
Run this code on a server or trusted worker. Never ship the LlamaGen bearer token in a browser bundle.
Get a key and copy the codeAccount, API key, usage, and billing open on LlamaGen.AI.
Verifiable request
Node.js create-and-poll example
JavaScript
const headers = {
Authorization: `Bearer ${process.env.LLAMAGEN_API_KEY}`,
"Content-Type": "application/json",
};
const created = await fetch("https://api.llamagen.ai/v1/comics/generations", {
method: "POST",
headers,
body: JSON.stringify({ prompt: "A four-panel launch story", fixPanelNum: 4 }),
}).then((r) => r.json());
let result = created;
while (["QUEUED", "PROCESSING"].includes(result.status)) {
await new Promise((resolve) => setTimeout(resolve, 2000));
result = await fetch(`https://api.llamagen.ai/v1/comics/generations/${created.id}`, { headers }).then((r) => r.json());
}Structured response
State your application can route
response.jsonPROCESSED
{
"id": "gen_abc123",
"status": "PROCESSED",
"comics": [
{
"page": 0,
"panels": [
{
"panel": 0,
"caption": "The team ships the launch.",
"assetUrl": "https://cdn.llamagen.ai/comics/panel-1.webp"
}
]
}
]
}Output evidence
Inspect the visual result and the machine-readable state.
The visual is evidence of the output category. The JSON is what lets an application correlate the generation, render a preview, store assets, and continue the workflow.
Capability and boundary facts
Facts an integration can verify.
Last verified:
- Endpoint
- POST /v1/comics/generations
- Authentication
- Bearer API key
- Lifecycle
- QUEUED → PROCESSING → PROCESSED or FAILED
- Delivery
- Poll by generation ID or use a callback URL
- Runtime
- Node.js or another trusted server runtime with fetch
Good fit
Use it when
- Node.js backends
- Serverless functions
- Queue workers
Wrong fit
Do not use it for
- Browser-only applications with an exposed token
- Infinite polling loops
- Ignoring non-2xx responses
Production limits
Plan for the boundaries.
- 01Add bounded polling, abort signals, and response checks before production use.
- 02Store secrets in the deployment platform's server-side environment settings.
- 03Generation is asynchronous; production interfaces must handle processing and failure states.
- 04Outputs should be reviewed against product, brand, safety, and print requirements before delivery.
- 05You must have the rights to prompts, photos, scripts, and reference assets submitted to the API.
Authoritative sources
Next step
Move from evidence to a real API request.
LlamaGen provides the playground, API key, usage, billing, and authoritative service documentation.
Get a key and copy the code