Indian Flag
Government Of India
A-
A
A+
Home/Models/Varya v1 Video Model
ownerRakesh V
organizationAvataar.AI (Soul Vision Creations Private Limited)
ORGANISATION

Varya v1 Video Model

Varya is a 14B distilled video generation model, at 10x+ the cost efficiency of leading models, India-tuned.

About Model

Varya is a 14B video generation model, distilled from Wan 2.2, to make frontier video AI affordable at population scale. Developed using a novel distillation technique, Varya generates video from text and image inputs at 10x+ greater cost efficiency than leading models while preserving comparable output quality. It is trained to represent India’s regional diversity- festivals, clothing, architecture, food, and traditions, across its visual outputs. Varya 1.0 is released as open weights under the Varya OpenRAIL-M License, permitting commercial use subject to responsible-use restrictions.

For more information, visit https://varya.avataar.ai

Varya v1 Video Model

Metadata Metadata

Varya OpenRAIL-M License

Avataar AI

Video Generation Model

PyTorch

Open

Avataar.AI (Soul Vision Creations Private Limited)

Sector Agnostic

04/11/26 12:52:58

Rakesh V

0

config_high_i2v.json ( 250 Bytes )

To preview this file, you need to be a registered user. Please complete the registration process to gain access and continue viewing the content.

Activity Overview Activity Overview

  • Downloads0
  • Downloads 0
  • File Size 0
  • Views 71

Tags Tags

  • Video

License Control License Control

Varya OpenRAIL-M License

Version Control Version Control

FolderVersion 1(0)
  • admin·1 day(s) ago
    • application/json
      config_high_i2v.json
    • application/json
      config_high_t2v.json
    • application/json
      config_low_i2v.json
    • application/json
      config_low_t2v.json
    • undefined
      high_noise_i2v.safetensors
    • undefined
      high_noise_t2v.safetensors
    • undefined
      low_noise_i2v.safetensors
    • undefined
      low_noise_t2v.safetensors

More Models from Avataar.AI (Soul Vision Creations Private Limited) More Models from Avataar.AI (Soul Vision Creations Private Limited)

Varya v1 Video Model
Varya is a 14B distilled video generation model, at 10x+ the cost efficiency of leading models, India-tuned.
Video
  • See Upvoters0
  • Downloads0
  • File Size0
  • Views72
Updated Today
AVATAAR.AI (SOUL VISION CREATIONS PRIVATE LIMITED)
View Details
share
Vegetation-Outlook-model
Forecasts vegetation greenness (NDVI) ~3 months ahead for locations across India. A Temporal Fusion Transformer on a frozen Prithvi-EO-2.0-300M backbone (LoRA-adapted). Per location and as-of date it outputs a predicted NDVI plus a relative vegetation-condition class (Below, Near, or Above normal) vs the site's own seasonal normal. Weights self-contained (no separate Prithvi download); repo code needed to run. Code: github.com/SoulVisionCreations/ndvi-forecasting-advisory
NDVI
time series analysis
  • See Upvoters0
  • Downloads7
  • File Size1.25 GB
  • Views159
Updated 2 month(s) ago
AVATAAR.AI (SOUL VISION CREATIONS PRIVATE LIMITED)
View Details
share
Groundwater-level-forecasting-model
Ground Water Level Forecasting Model for India. Given a location and as-of date, it forecasts the change in depth-to-water (metres) over the next 3 and 6 months, interpolated from the nearest monitored wells. Code and setup (see docs/ADVISORY.md): https://github.com/SoulVisionCreations/gwl-forecasting-advisory
Remote Sensing
Groundwater Monitoring
  • See Upvoters0
  • Downloads8
  • File Size1.19 GB
  • Views213
Updated 2 month(s) ago
AVATAAR.AI (SOUL VISION CREATIONS PRIVATE LIMITED)
View Details
share

© 2026 - Copyright AIKosh. All rights reserved.