Alibaba Tongyi Lab (Wan)
Alibaba Tongyi Lab (Wan) has 7 models in this directory, covering editing and post and video generation.
Alibaba's Tongyi Lab publishes the Wan family of video generation models. Wan 2.1 and Wan 2.2 (plus Wan-Animate) are released as open weights under Apache-2.0 on GitHub, Hugging Face and ModelScope. Later versions (Wan 2.5 onward) are API-only via Alibaba Cloud Bailian and are not open weights.
Every one of their models catalogued here ships weights you can download. That does not by itself mean you may use the output commercially — read each licence.
At a glance
- Headquarters
- China
- Founded
- 1999
- Models here
- 7
- Categories
- video
Their models in this directory
Wan 2.1 T2V (1.3B and 14B)
The first widely adopted Apache-2.0 video generation family. T2V-1.3B generates 480P and fits in about 8.19GB of VRAM; T2V-14B handles 480P and 720P.
Video generation
Wan 2.1 VACE (1.3B and 14B)
An all-in-one video creation and editing model built on the Wan 2.1 backbone. It handles reference-to-video, video-to-video restyling, masked inpainti
Editing and post
Wan 2.2 I2V-A14B
Animates a still image into video, optionally guided by a text prompt, using the same 27B/14B-active mixture-of-experts architecture as the text-to-vi
Video generation
Wan 2.2 S2V-14B
Audio-driven video generation: takes a reference image plus an audio track and produces a speaking or performing subject synchronized to that audio. O
Video generation
Wan 2.2 T2V-A14B
Generates video from a text prompt using a mixture-of-experts diffusion transformer with 27B total and 14B active parameters, split into a high-noise
Video generation
Wan 2.2 TI2V-5B
A 5B-parameter dense model that handles both text-to-video and image-to-video in one checkpoint. It uses the Wan2.2-VAE with a 16x16x4 compression rat
Video generation
Wan-Animate-2
Character animation and replacement driven directly by a video. It consumes the driving video inside a redesigned diffusion transformer rather than go
Video generation
How to prompt it
Written for Alibaba Tongyi Lab (Wan). See prompt craft for the full vocabulary and cinematic language for the lens, light and mood tables.
-
Wan 2.7
Synchronized audio with character-consistent video (2.7); stylized, experimental, intentionally artistic cheap work (2.6).
Some Wan configs are prompt-only and reject media inputs.
MCP servers that front Alibaba Tongyi Lab (Wan)
Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.
-
370.ai, AI Gateway: Video (Seedance 2.0, Wan, HappyHorse), Image, Speech + 100+ Chat Models
One key, 100+ models, chat with any LLM and generate video, images, speech. Free trial at 370.ai.
-
Aetherwave
Music, image, video and audio generation across top AI providers - one key, one credit pool.
-
Clipia
Generate AI images, video, speech, music and presentations from Claude, ChatGPT and Cursor.
-
Fal
Create and edit high-quality media across various formats including images, videos, audio, and 3D models.
-
Filtrix AI MCP
Filtrix MCP for image/video generation. Portal.
-
Higgsfield
Create images and videos from a prompt inside any MCP compatible AI tool.
-
Kie
MCP for kie.ai: 45+ image, 70+ video, 20+ audio models with model intelligence.
-
OpenArt
Generate AI images and video from any agent, with OAuth and no API keys.
-
Picsart GenAI
Generate and edit images, videos and audio with 150+ AI models.
-
Replicate
Replicate MCP server - image, video, audio, speech, LLM, vision, upscale, 3D, training. 36 tools.
-
Runcomfy
Remote MCP server for RunComfy Serverless API (ComfyUI): deployments and async inference.
-
Switch
Generate, manage and explore your Switch AI image and video library, scoped to your account.