Avataar logo

Avataar models

Avataar is a Bengaluru AI company that built Varya, a distilled video generation model, with compute support from the IndiaAI Mission.

Bengaluru, Indiaavataar.ai

Releases
1
Open weights
0
Latest
Jun 12, 2026

June 2026

1 release
  1. VideoProprietary

    Varya

    Varya is Avataar's distilled video generation model, which turns text prompts, reference images and audio into short clips that can be extended into multi-clip stories.

    Modalities
    text, image, audio → video
    • As of November 2026 the Varya site generated clips of 1 to 15 seconds at 480p or 760p
    • Supports first and last frame control, up to five reference images plus one audio clip, and continuing a video for up to six clips
    • As of November 2026 the site described the model as distilled and post-trained on Minimax H3
    • The API was priced at ₹1 per second at 480p and ₹2 per second at 760p in November 2026, with watermarked output
    Source: Varya Video generation model

Cite and reuse this data

These release records are free to reuse under CC BY 4.0, including commercially. Credit The AI Engineering and link to this page's URL.

Dates are the labs' official announcement dates, and every record links to its source. List fields in the CSV are separated by " | ".

Citation

The AI Engineering Editors. "Avataar models: release history and timeline." The AI Engineering, updated Jun 12, 2026. https://theaiengineering.com/releases/avataar

HTML link

<a href="https://theaiengineering.com/releases/avataar">Avataar models: release history and timeline</a> (The AI Engineering)
Full dataset
1,250 releases from 73 labs
Coverage
to
Updated
License
CC BY 4.0
Publisher
The AI Engineering

Other labs