We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
tbc/mischief-1Runs on your balance at the prices above. New accounts start with free usage.
Settings
TBC: Mischief 1 is a video generation model from TBC, The Biological Computing Co. It is described as a neuron-derived video model, and it is built specifically for turning visual and textual input into short video clips. If you are working on a pipeline that needs generated motion rather than generated stills, this is the model in TBC's lineup aimed at that job.
The model accepts text and images as input and produces video as output. It supports image to video generation, and the image input can be used as a first frame, which gives you a way to anchor the opening shot of a clip to a specific still. Output resolutions are 480p and 720p, the aspect ratio is 16:9, and clip durations are 3 or 5 seconds. Audio generation is not supported, so any sound has to be added downstream. A context window is not listed for this model.
Those capabilities point to a fairly specific set of uses. Because a first frame image is accepted, the model fits workflows where you already have a key visual, such as a product shot, a character still, a storyboard panel or a thumbnail, and you want it brought to life as a short clip. The 16:9 framing and the 3 or 5 second durations suit social and web video slots, animated previews, and quick concept visualisations where you need to test how a shot reads in motion before committing to a longer production. Text input lets you steer what happens within the clip, so prompt-driven variations on the same starting frame are practical.
You call the model through api14's OpenAI-compatible API using the model id "tbc/mischief-1". The supported request parameters are max_tokens and temperature. Because the interface follows the OpenAI format, you can point existing OpenAI-style client code at api14 and change the model id rather than rewriting your integration.
It is worth checking the model against your requirements before you commit. There is no audio output, so projects that need synchronised sound will require a separate step. Only the 16:9 aspect ratio is available, which rules out vertical or square formats unless you crop or pad afterwards, and the duration options are limited to 3 and 5 seconds. If your work depends on longer clips, other aspect ratios or generated audio, a different model is likely to be a better fit.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
// Video generation is asynchronous: submit, then poll until completed.
let job = await client.post("/videos", { body: {
"model": "tbc/mischief-1",
"prompt": "A drone shot over turquoise ocean waves at sunrise",
"duration": 8,
"resolution": "720p",
"aspect_ratio": "16:9"
} });
while (!["completed", "failed"].includes(job.status)) {
await new Promise((r) => setTimeout(r, 5000));
job = await client.get(`/videos/${job.id}`);
}
console.log(job.status, job.unsigned_urls);
max_tokenstemperatureThis community has no topics yet. Open the first one about TBC: mischief 1.