About Wan2.2 5B - Text to Video
Wan-AI/Wan2.2-TI2V-5B-Diffusers is a video generation model that supports both text-to-video and image-to-video synthesis at 720P resolution and 24fps. It excels in efficient high-definition video generation on consumer-grade GPUs, balancing speed, quality, and resource consumption, making it suitable for both industrial and academic applications.
Some other noteworthy features of Wan-AI/Wan2.2-TI2V-5B-Diffusers include support for unified text-to-video and image-to-video tasks within a single framework, as well as a high-compression VAE architecture that enables fast generation of five-second 720P videos in under nine minutes on typical hardware.
| Metric | Value |
|---|---|
| Parameter Count | 5 billion |
| Mixture of Experts | No |
| Multilingual | No |
| 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 Wan2.2 5B - Text to Video?
Try Wan2.2 5B - 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-wan2-2-ti2v-5b-diffusers",
"prompt": "A beautiful landscape painting of a serene lake with mountains in the background and an ox in the foreground.",
"height": 720,
"width": 1280,
"negative_prompt": " ",
"num_inference_steps": 30,
"num_frames": 81,
"guidance_scale": 5
}'Request parameters
Every field Wan2.2 5B - Text to Video accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/videos/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Prompt for generated image |
height | integer | No | 720 | Height of the video Range: 1 – 720 |
width | integer | No | 1280 | Width of the video Range: 1 – 1280 |
negative_prompt | string | No | — | Negative prompt for generated image |
num_inference_steps | integer | No | 30 | Number of diffusion steps to take Range: 1 – 100 |
num_frames | integer | No | 81 | Number of frames of video to generate Range: 1 – 120 |
guidance_scale | number | No | 5 | Guidance for generated video. Lower values can give more realistic videos. Range: 0 – 10 |
seed | integernullable | No | — | Random seed. Set for reproducible generation |