Alibaba

Creators of the Happy Horse, Qwen and Wan model families - open-weight image and video generation from Alibaba's Tongyi Lab

Operational

Models on fal

Abot World

1 variant available

1 new

alibaba/abot-world-0

New

worlds

Price$0.00125/compute seconds

Wan 3.0

6 variants available

alibaba/wan-3.0-prime/text-to-video

text-to-video

Price$0.05/s

alibaba/wan-3.0-prime/reference-to-video

video-to-video

Price$0.05/s

alibaba/wan-3.0-prime/image-to-video

image-to-video

Price$0.05/s

alibaba/wan-3.0/reference-to-video

video-to-video

Price$0.05/s

alibaba/wan-3.0/image-to-video

image-to-video

Price$0.05/s

Qwen 3

6 variants available

Qwen Image 3

2 variants available

Happy Horse

7 variants available

Wan 2.7

8 variants available

Z-Image

14 variants available

Wan Trainer

5 variants available

Wan 2.2

24 variants available

Wan 2.6

7 variants available

Qwen Image

2 variants available

Qwen

39 variants available

Wan

16 variants available

Wan 2.5

4 variants available

About

Alibaba's generative models come out of Tongyi Lab, the AI research division of Alibaba Cloud. The lab develops the Qwen family, the brand Alibaba has unified its large-model work under, alongside the Wan video models, originally launched as Tongyi Wanxiang. Many are released open-weight under permissive licenses, making them a popular foundation for developers and the open-source community.

On the visual side, Qwen-Image is a text-to-image foundation model known for state-of-the-art complex text rendering, while Qwen-Image-Edit brings precise, instruction-driven image editing.

In video, the Wan series spans text-to-video and image-to-video generation, with Wan 2.5 introducing native synchronized audio and later versions adding reference-to-video, multi-shot control, and flexible aspect ratios.

Notable model families on fal:

Happy Horse: text- and image-to-video, with native audio generation
Qwen-Image: text-to-image with leading text rendering
Qwen-Image-Edit: instruction-based image editing
Wan 2.1 / 2.2 / 2.5 / 2.6: text- and image-to-video, some with native audio
Wan-Animate: character animation driven by reference video

Try it in fal Sandbox

A breathtaking ancient monastery floating among massive clouds thousands of feet above the earth. Golden sunrise light pierces through the atmosphere, illuminating towering stone structures connected by elegant bridges suspended in the sky. Monks in flowing robes walk along the pathways while giant birds glide through the clouds below. Epic fantasy architecture, cinematic composition, volumetric lighting, god rays, immense scale, ultra-detailed stonework, dreamlike atmosphere, photorealistic rendering, masterpiece environment design, Unreal Engine 5 quality, 8K.

fal-ai/z-image/base

fal-ai/qwen-image-2512+1

Try it on Sandbox

A classic red Ferrari parked along a winding cliffside road on Italy's Amalfi Coast during golden hour. The Mediterranean Sea sparkles beneath dramatic coastal cliffs while colorful villages cling to the mountainside in the distance. Warm sunlight reflects off the polished bodywork. Luxury travel meets automotive photography, cinematic composition, rich Mediterranean colors, photorealistic details, Vogue travel editorial aesthetic, ultra-sharp focus, depth and atmosphere, award-winning commercial photography, 8K masterpiece.

fal-ai/wan/v2.7/text-to-image

fal-ai/z-image/base+1

Try it on Sandbox