Name: VEED Fabric 1.0 API
Brand: VEED

Overview

Model Overview

VEED Fabric 1.0 is a state-of-the-art generative AI model designed to transform static images into realistic talking videos with expressive, lip-synced, and emotion-rich animated characters. It supports a broad range of image styles from photos to illustrations and mascots and synchronizes mouth, facial expressions, head, and body movements with an audio voice input. Fabric 1.0 notably advances video creation by being significantly faster and cheaper than prior solutions, making it ideal for creators, marketers, and enterprises seeking cost-effective video production at scale.

Technical Specifications

Architecture: Diffusion Transformer (DiT)
Input image formats: jpg, jpeg, png, webp, gif, avif (max 10MB)
Audio input formats: mp3, ogg, wav, m4a, aac (max 10MB)
Video output format: mp4
Supported resolutions: 480p and 720p (16:9 aspect ratio) plus others like 1:1, 4:3, 3:4, 9:16 with scaled resolutions
Frame rate: 25 FPS
Maximum video length: 60 seconds

Performance Benchmarks

Approximately 7x faster generation speed than average image-to-video models
High fidelity lip synchronization and expressive motion reduce unnatural or stiff animations
Supports complex dialogues and emotionally rich speech

Key Features of VEED Fabric 1.0

Transforms any static image (photo, illustration, character render) into a realistic talking video
High-quality lip-sync synchronized precisely with the provided audio input
Natural facial expressions, including eye movements, head nods, and body gestures
Supports multiple video aspect ratios including 16:9, 1:1, 9:16 with resolutions of 480p and 720p
Video output in widely compatible MP4 format at 25 FPS
Fast video generation: around 1.5 minutes per 10 seconds of 480p video
Uses advanced diffusion-transformer architecture for expressive, natural movement

API Pricing

480p: $0.104;
720p: $0.195

Use Cases

Explainer and educational videos: Create engaging face-to-camera presentations from text or blog content for online learning and tutorials
Marketing and social media: Produce branded talking videos and ad variations quickly and cost-effectively for platforms like TikTok, Instagram, and YouTube Shorts
Animated mascots and characters: Bring brand mascots or fictional characters to life without manual animation pipelines
Personalized video at scale: Generate customized messages for different audience segments automatically
Internal and external corporate communication: Use AI avatars as spokespeople or for training materials without the need for video shoots
Content creation for creators and influencers: Quickly produce polished talking head videos without filming, reducing production time and costs drastically

Generation Code Sample

Output Code Sample

Comparison with Other Models

vs Kling AI Avatar: VEED Fabric 1.0 offers faster generation speeds and cost-efficient production for marketers and educators, with high fidelity lip-sync and natural gestures. Kling AI Avatar focuses more on cinematic realism and emotional depth, ideal for storytellers seeking highly nuanced character expressions.

vs Synthesia: VEED Fabric 1.0 animates any static image with natural lip-sync and expressive gestures, supporting diverse input styles and longer videos. Synthesia primarily offers a library of preset avatars for corporate and educational videos with more limited creative input flexibility.

vs HeyGen: VEED Fabric excels in flexibility of input images and faster generation speeds, suited for marketing, creators, and educators requiring multiple video variations quickly. HeyGen provides high-fidelity digital avatars with a focus on localized languages and interactive dialogue systems for advanced virtual communication.

vs Hour One: VEED Fabric offers broad creative freedom by animating any static image plus integrated editing tools for fast content workflows. Hour One is more focused on enterprise virtual spokespersons and language synthesis integration for automated corporate videos.

API Integration

Accessible via AI/ML API. Documentation: available here.

Use cases

Explainer and educational videos: Create engaging face-to-camera presentations from text or blog content for online learning and tutorials
Marketing and social media: Produce branded talking videos and ad variations quickly and cost-effectively for platforms like TikTok, Instagram, and YouTube Shorts
Animated mascots and characters: Bring brand mascots or fictional characters to life without manual animation pipelines
Personalized video at scale: Generate customized messages for different audience segments automatically
Internal and external corporate communication: Use AI avatars as spokespeople or for training materials without the need for video shoots
Content creation for creators and influencers: Quickly produce polished talking head videos without filming, reducing production time and costs drastically

‍

How to use VEED Fabric 1.0 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to veed/fabric-1.0.

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",
      "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",
    "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","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.