Krea WAN 14B is a next-generation large-scale AI video model designed for real-time video creation, transformation, and interactive editing. Built on a 14-billion-parameter architecture, it enables creators, developers, and studios to generate and modify video content with unprecedented speed, responsiveness, and creative control.
Text-to-Video mode allows users to generate original video content directly from natural language prompts. A short textual description is enough to produce a dynamic visual sequence that reflects the scene, style, atmosphere, and motion described by the user.
This workflow is particularly well-suited for early-stage ideation, storytelling, marketing concepts, and cinematic previews. Because generation happens in real time, prompts can be refined mid-process, enabling fast creative exploration without restarting or waiting for full renders.
Video-to-Video mode focuses on transforming existing footage rather than creating video from scratch. Users provide a source video and guide the transformation through prompts that define style, mood, visual enhancements, or artistic direction.
Instead of replacing the original motion, the model preserves temporal structure and movement while reinterpreting the visuals. This makes Video-to-Video ideal for stylization, creative iteration, visual upgrades, and concept revisions, especially in professional production pipelines.
Krea WAN 14B fits naturally into modern creative and technical workflows. Content creators can prototype visuals for social media, ads, and storytelling in minutes rather than hours. Designers and filmmakers can iterate on styles, moods, and effects before committing to final production. Developers can embed real-time video generation into applications, tools, and interactive experiences.
vs Wan 2.1: Krea WAN 14B is a much larger, 14-billion parameter model compared to Wan 2.1's 1.3 billion parameters. This size boost translates directly into far superior modeling of complex movements and high-frequency video details.
vs Wan 2.1 Turbo: Krea WAN 14B excels in live, prompt-interactive video generation with streaming edits, whereas Turbo focuses on throughput and higher resolution batch generation with less on-the-fly interaction.
vs Veo 3.1: While Veo 3.1 produces high-quality long-form videos, it does not support real-time streaming or interactive generation, making Krea WAN 14B more suitable for creative workflows requiring immediate feedback. Krea's model is also open-source, enabling greater transparency and modification compared to Google's proprietary Veo system.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v2/video/generations", headers=headers, json={ "model": "krea-wan-14b/text-to-video", "prompt": "A serene timelapse of clouds over a mountain range" }, ).json() gid = job["id"] while True: res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json() if res.get("status") in ("completed", "error"): break time.sleep(5) print(res["video"]["url"])
const headers = { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", { method: "POST", headers, body: JSON.stringify({ "model": "krea-wan-14b/text-to-video", "prompt": "A serene timelapse of clouds over a mountain range" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 5000)); res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json(); } while (!["completed", "error"].includes(res.status)); console.log(res.video.url);
# submit the generation — the response contains the job "id" curl -X POST https://api.aimlapi.com/v2/video/generations \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"krea-wan-14b/text-to-video","prompt":"A serene timelapse of clouds over a mountain range"}' # then poll until status is "completed" — video.url holds the result curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Krea WAN 14B This page | Video generation |
Krea WAN 14B takes text as input and returns video.
Krea WAN 14B is priced at $0.0325 / sec (variable).
Krea WAN 14B is billed per generation — a fixed charge per output rather than by prompt length.
Krea WAN 14B was built by Krea.
Send a request to v2/video/generations with krea-wan-14b/text-to-video as the model id.
Yes. Krea WAN 14B is served through AI/ML API, so the same key and endpoint format used for other models applies.
-min.webp){kind=small}
