About Wan2.1 14B - Text to Video
Wan-AI/Wan2.1-T2V-14B-Diffusers is a 14B parameter Large Vision Model (LVM) designed for high-fidelity text-to-video and image-to-video generation, including support for readable text in English and Chinese within generated videos.
It excels in generating temporally consistent videos from detailed prompts, offers customizable aspect ratios, and maintains stability at both 480p and 720p resolutions across consumer-grade hardware.
Some other noteworthy features of Wan-AI/Wan2.1-T2V-14B-Diffusers include prompt enhancement for improved video quality and precision, and efficient video encoding via a variational autoencoder (VAE). Output video is silent; it does not generate audio.
| Metric | Value |
|---|---|
| Parameter Count | 14 billion |
| Mixture of Experts | No |
| Multilingual | Yes |
| Quantized* | No |
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
Ready to build with Wan2.1 14B - Text to Video?
Try Wan2.1 14B - Text to Video in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -X POST https://hub.oxen.ai/api/ai/videos/generate \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OXEN_API_KEY" \
-d '{
"model": "wan-ai-wan2-1-t2v-14b-diffusers",
"prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground.",
"height": 480,
"width": 832,
"negative_prompt": " ",
"num_inference_steps": 16,
"num_frames": 81,
"guidance_scale": 5
}'