VEED Fabric 1.0 on fal: Image-to-Video Model for Talking Characters

ArticleTeam falAnnouncement

VEED has released Fabric 1.0 on fal. The model turns any still image into a talking video driven by audio or text, synchronising lip, head, hand, and body movements.

Key points

  1. Fabric 1.0 is an image and speech audio to video model powered by a Diffusion Transformer (DiT).
  2. Audio input drives not only lip synchronisation but also body, hand, and head motion matching the spoken rhythm.
  3. Works with any custom source image, including photos, illustrations, mascots, and 3D renders, rather than preset stock avatars.
  4. Technical specifications: input image and audio files under 10 MB, maximum video length of 1 minute at 25 FPS in 480p or 720p.
  5. Generation speeds take roughly 1.5 minutes for 10 seconds of 480p video, and around 5 minutes for 720p.
  6. An API is available on fal for programmatic video generation and automated pipelines.

Why it matters

Most talking-head generators restrict users to a limited set of pre-recorded stock avatars. Fabric 1.0 allows creators and developers to animate custom branding, mascots, or arbitrary characters via an API without custom video shoots.

Analysis

By conditioning on the first frame for style and using speech audio to direct sequence continuation, the Diffusion Transformer architecture delivers natural movement across different aspect ratios. However, rendering times of up to 5 minutes for 10 seconds of 720p footage mean integrations must be designed around asynchronous background processing.

Mentioned links

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Related entries

Similar in content, found by the AI search.

  • Link:VEED

    VEED: Browser-Based Platform for AI Video Creation and Editing

    VEED provides a browser-based suite for creating and editing video content via generative AI. The platform combines text-to-video generation, AI avatars, automated subtitles, eye contact correction, and developer APIs.

    AI & LLMs· Tool

  • Link:veed.io

    VEED integrates leading AI video models into its editing suite

    Online video platform VEED has integrated multiple generative video models—including Google Veo 3.1, Kling O1, Hailuo, and OpenAI Sora—directly into its editing environment. Users can generate video from text prompts, scripts, or images and immediately refine the output with subtitles, voiceovers, and branding.

    AI & LLMs· Tool

  • Link:ElevenLabs

    ElevenLabs Unveils Eleven v4 Model and Expands Voice Agent Ecosystem

    ElevenLabs has announced its Eleven v4 model alongside an expanded platform structure comprising ElevenCreative for multimodal media production, ElevenAgents for conversational customer interactions, and dedicated developer APIs.

    AI & LLMs· Tool

  • Link:ElevenLabs

    ElevenLabs Platform Overview: ElevenAgents and Eleven v4 Launch

    ElevenLabs presents Eleven v4 alongside its core platform structure, consisting of ElevenCreative for audio and media generation, ElevenAgents for conversational AI agents across multiple communication channels, and developer APIs.

    AI & LLMs· Tool

Back to the knowledge base

Let's talk about your project

Get in touch

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.