VEED Fabric-1.0 Fast leverages advanced Diffusion Transformer (DiT) technology to transform one still image into a dynamic, talking video avatar. It supports a wide variety of image styles, including photographs, illustrations, and mascots. The model offers fast video generation, making it ideal for marketing, social media, virtual presentations, and e-learning.
vs Veo 3: VEED offers intuitive image-to-video conversion with expressive avatars targeting marketing and social media content creators. Veo 3 API competes with broad AI video processing features including fast inference but is more API-heavy, catering to developers building customized AI video pipelines rather than end-user video generation.
vs Kling AI Avatar: VEED Fabric-1.0 Fast excels in speed and cost efficiency, generating talking videos from any single image in about 1.5 minutes per 10 seconds, supporting multiple styles including photos and illustrated characters. Kling AI Avatar specializes in cinematic, emotionally rich avatar animations but is slower and more focused on streaming and creative storytelling applications.
vs Sonix AI: While VEED focuses on fast avatar video generation with strong lip-sync and facial animation, Sonix AI is a leader in highly accurate transcription and subtitle generation supporting 53+ languages, aimed at professional content workflows. Sonix offers superior transcription precision but does not provide avatar video generation like VEED.
Accessible via AI/ML API. Documentation: available here.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v2/video/generations", headers=headers, json={ "model": "veed/fabric-1.0/fast", "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 ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", { method: "POST", headers, body: JSON.stringify({ "model": "veed/fabric-1.0/fast", "prompt": "A serene timelapse of clouds over a mountain range" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 5000)); res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${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":"veed/fabric-1.0/fast","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 |
|---|---|---|---|---|
VEED Fabric-1.0 Fast This page | Video generation |
VEED Fabric-1.0 Fast takes image, text, video as input and returns video.
VEED Fabric-1.0 Fast became available on November 24, 2025.
VEED Fabric-1.0 Fast is priced at $0.13 / sec (variable).
VEED Fabric-1.0 Fast is billed per generation — a fixed charge per output rather than by prompt length.
Yes, VEED Fabric-1.0 Fast accepts image input as well as a text prompt.
VEED Fabric-1.0 Fast was built by VEED.
Use veed/fabric-1.0/fast as the model id on AI/ML API.
Yes. VEED Fabric-1.0 Fast is served through AI/ML API, so the same key and endpoint format used for other models applies.
It is a video generation model that converts image, text, and video inputs into video output.
-min.webp){kind=small}
