text-to-video
Wan 2.2 T2V 5B is a 5B text-to-video model with LoRA support that generates 720p videos from text prompts for easy personalization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
Your request will cost $0.1 per run.
For $1 you can run this model approximately 10 times.
One more thing::
ExamplesView all
README
Wan 2.2 t2v-5b-720p-lora
Wan 2.2 T2V 5B is a 5B-parameter text-to-video model with LoRA support that generates 5-second, 1280×720 videos from text prompts. It is built on WAN AI’s Mixture of Experts (MoE) architecture, combining high-noise and low-noise experts across denoising timesteps for sharp details, smooth motion, and strong cinematic style.
Why it looks great
- Cinematic-level aesthetic control Tuned to professional filmmaking standards, with rich control over lighting, color palette, composition, lens, and camera movement.
- Large-scale complex motion Handles dramatic actions, character interactions, and challenging camera paths while keeping motion stable and natural.
- Precise semantic compliance Strong scene understanding and multi-object generation, so shots stay close to your story beats and prompt.
- 5B parameter backbone Higher texture fidelity, better character consistency, and improved temporal coherence across frames.
Pricing
- Flat price: $0.10 per run
How to Use
-
In the prompt box, describe the scene, characters, motion, camera, lighting, and style in detail.
-
(Optional) Click Add Item under loras to attach up to 3 LoRA adapters.
- In each LoRA slot, paste the LoRA path (owner/model-name) or a direct
.safetensorsURL. - Use the scale slider to control strength (for example, 0.6–1.0 for most character or style LoRAs).
- In each LoRA slot, paste the LoRA path (owner/model-name) or a direct
-
Choose the size 1280×720 or 720×1280.
-
Set the seed
-
Click Run. After generation finishes, preview the video on the right panel and download it if you are satisfied.