Text or image to video
Describe a video in words, or add an image and a text prompt.
Create a video from a description
Wan2.2 is an advanced AI video generation model developed by Alibaba's Institute for Intelligent Computing. It features a Mixture-of-Experts (MoE) architecture, which enhances video quality and efficiency. Key capabilities include: Cinematic-level aesthetics: Incorporates curated aesthetic data for precise visual style control. 1- Complex motion generation: Trained on a significantly larger dataset, enhancing generalization across motions, semantics, and aesthetics. 2- Efficient high-definition hybrid TI2V: Supports text-to-video and image-to-video generation at 720P resolution with 24fps, running on consumer-grade graphics cards. 3- Open-source model: The TI2V-5B model achieves a compression ratio of 16×16×4, making it one of the fastest 720P@24fps models available.
Opens the video studio with WAN 2.2 · Variant 2 ready to use. You will need a free account to run it.
What it makes
Create a video from a description
Turns a written description into a short video.
What you need
Optional: a picture to start from.
What you get
A short video clip
WAN 2.2 makes a video from a written description or from an image you add. It has two modes, Text to Video and Image to Video, and you get the finished video back.
Image to Video needs an image and a text prompt to guide it. Its one setting is Duration (seconds), which has two choices, 81 and 161. Text to Video has five settings. Aspect Ratio offers 16:9, 9:16, 1:1 and 4:3. Duration (seconds) offers 81 and 161. Style offers cinematic, animated, realistic, artistic, anime and abstract. Motion Scale is a number from 0 to 10 that starts at 5. Frame Rate offers 16 and 24.
WAN 2.2 costs 400 credits. LTX 2.3 costs 3030-4000 credits and includes a mode that works from an audio clip.
Same job: create a video from a description. Compare before you choose.
MiniMax Video-01 turns text prompts into cinematic 720p clips in seconds, with smooth motion and dynamic camera work. No filming or editing skills needed.
MiniMax Video-01-Live is a text-to-video generation model that creates high-quality MP4 video clips with built-in prompt optimization for improved visual coherence and motion fidelity.
MiniMax Hailuo-2.3 Pro is an advanced text-to-video generation model that creates high-quality 1080p video with strong prompt understanding, cinematic motion, and support for detailed action and audio-aware prompts.
PixVerse v5 is a high-quality text-to-video generation model that creates video clips from text prompts, with support for multiple resolutions including 360p, 540p, 720p, and 1080p.
Describe a video in words, or add an image and a text prompt.
Choose cinematic, animated, realistic, artistic, anime or abstract. It starts at cinematic.
Text to Video offers 16:9, 9:16, 1:1 and 4:3.
Choose Text to Video, or Image to Video if you have an image.
For Image to Video, add an image and a text prompt. For Text to Video, write your description, then set Aspect Ratio, Duration, Style, Motion Scale and Frame Rate.
Start the run for 400 credits and get your video back.
Add an image and a text prompt to guide the video.
Use Text to Video to turn a scene in words into a clip.
Quick answers to help you get the most out of WAN 2.2 · Variant 2 in FunAI Studio.