The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestQwen · Alibaba2.2-Animate-2
Qwen · AlibabaImage → Video

Alibaba's Wan2.2-Animate-2 14B lands under Apache 2.0

A permissively licensed 14B video model aimed at character animation joins the growing Wan family.

Jul 14, 2026
NotableApache 2.0
Wan2.2-Animate-2 14B

Alibaba's Wan team has published Wan2.2-Animate-2 14B on Hugging Face, adding another entry to its expanding lineup of open video models. The release is a 14-billion-parameter dense model — not a mixture-of-experts design — released under the permissive Apache 2.0 license.

The model is built for animation-oriented generation, supporting both image-to-video and text-to-video workflows. Its primary focus is turning a still image into motion, a task that has become one of the more competitive corners of open-source generative video.

Why it matters

Apache 2.0 licensing is the notable detail here. Many capable video models arrive with usage restrictions, so a permissive license lowers the barrier for developers and studios who want to build on, fine-tune, or deploy the model commercially without legal friction.

  • 14B dense parameters, no MoE
  • Image-to-video and text-to-video modalities
  • Apache 2.0 license
  • Part of Alibaba's ongoing Wan 2.2 series

As the Wan family continues to iterate, the Animate branch signals Alibaba's intent to compete specifically on character and image-driven animation rather than general text-to-video alone. Full details and weights are available on the model's Hugging Face page.

Sources

  • Wan-AI/Wan2.2-Animate-2-14B

    Hugging Face

    Visit
OlderNVIDIA's Nemotron 3 Embed tops the RTEB leaderboardNVIDIA · Embeddings · 4 months agoNewerCrisperWhisper 2.0 Large targets verbatim transcriptionNyralabs · Speech → Text · 4 months ago

Get the model

Hugging Face

Specs

Parameters14B
LicenseAPACHE-2.0
Likes390

Can you run it?

Runs on a laptop — about 15 GB at FP8.

  • BF16 (as published)

    32 GB GPU (RTX 5090) · 48 GB Mac

    29 GB
  • FP8

    16 GB GPU (RTX 4080 / 5070 Ti) · 24 GB Mac

    15 GB
Your machine
  • Precision not published; assuming 16-bit (BF16) weights.
  • Parameter count is an editorial estimate — no weights metadata on Hugging Face.
  • Covers the published checkpoint; text encoders and VAE loaded alongside may add a few GB (many runtimes offload them to CPU).

Estimated from the parameter count. Assumes an 8K context and ~1 GB runtime overhead; actual needs vary. How we estimate


Modalities

Image → VideoText → Video

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More from Qwen · Alibaba

All Qwen · Alibaba releases →
Qwen · Alibaba/Speech → Text

Qwen-Audio-3.1-ASR Adds Speaker-Aware Transcription

Alibaba's new open audio-language model transcribes and diarizes speech across 30 languages under an Apache 2.0 license.

Oct 19, 2026
Qwen-Image-2.1-Turbo
Qwen · Alibaba/Text → ImageRuns on a laptop

Qwen-Image-2.1-Turbo targets faster generation

Alibaba's Qwen team ships a distilled, few-step variant of its image model built for speed.

Oct 9, 2026
Qwen-Image-2.1
Qwen · Alibaba/Text → ImageRuns on a laptop

Qwen-Image-2.1 Adds RGBA to Image Generation

Alibaba's Qwen team updates its open image model with transparency support and joint text-to-image and editing capabilities.

Sep 14, 2026

More in Image → Video

All Image → Video →
LongCat-Video-Avatar-1.6
Meituan/Image → Video

Meituan's LongCat Adds Audio-Driven Avatar Video

The LongCat team releases an image-to-video model that animates still portraits from audio input.

Nov 13, 2026
NVIDIA/Image → Video

NVIDIA Releases Cosmos 3 for World Simulation

The new open models push NVIDIA's world-foundation effort toward interactive, real-time video generation.

Nov 5, 2026
NVIDIA/Text → Video

NVIDIA's Cosmos 3 Brings Open Interactive World Models

The new open release pushes beyond passive video generation toward simulated worlds that respond to input.

Nov 5, 2026