WAN 2.2 T2V 480p with LoRA generates text-to-video at 480p and supports custom LoRAs for personalized styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.2per run·~50 / $10
ExamplesView all
A bride stands in a softly lit room, adjusting her earrings in the mirror. Her traditional dress is rich in detail—silk, embroidery, delicate patterns. The camera focuses on her calm yet nervous expression. Intimate, elegant, photorealistic portraiture with cultural depth.
A young boy sits quietly on a moving bus, gazing out the rain-covered window. Water droplets trail down the glass as city lights blur in the background. His reflection is visible in the glass. Subtle breathing, real-time expression changes, tender moment, slice of life.
A professional chef swiftly chops vegetables, stirs a boiling pot, and wipes sweat from his brow. Other chefs rush in the background. Steam, sizzling, shouting—chaotic yet focused. Stainless steel surfaces reflect the light. Lifelike motion, high detail on hands and utensils.
A child runs through a sunlit wheat field, laughing. Her hair flies behind her, hands brushing the tall stalks. The camera follows from behind, capturing golden light and dust in the air. Innocent, energetic, poetic realism.
A boxer throws punches at a hanging bag in a dimly lit underground gym. Muscles tense, sweat drips, the bag swings with impact. Chalk dust rises from the floor. Camera cuts between close-ups of his hands, face, and full-body motion. Raw and gritty realism.
A teenage girl leans on her apartment balcony railing, headphones on, eyes closed. The wind gently sways her hair and oversized shirt. The city glows below in evening tones. Camera captures soft lens flares and subtle expressions. Realistic urban mood, serene yet cinematic.
A father sits beside his young daughter’s bed, reading a picture book to her. The child listens intently under a soft blanket, a small lamp glowing nearby. The camera gently pans from the book to their faces. Warm lighting, lifelike fabric and skin detail, tender family moment.
A man jogs through a foggy park at dawn. His breath is visible in the cold air, shoes rhythmically hitting the wet pavement. Trees blur in the mist behind him. The camera tracks from the side, highlighting muscle motion and condensation. Gritty, realistic atmosphere.
A young man stands on an empty subway platform, checking his phone. Flickering fluorescent lights, tiled walls, distant train rumble. His expression shifts from bored to alert. Over-the-shoulder and profile angles. Moody, cinematic realism with tension.
A bride stands in a softly lit room, adjusting her earrings in the mirror. Her traditional dress is rich in detail—silk, embroidery, delicate patterns. The camera focuses on her calm yet nervous expression. Intimate, elegant, photorealistic portraiture with cultural depth.
Related Models
README
Wan 2.2 Text-to-Video 480p LoRA
Create customized videos from text with full LoRA support using Wan 2.2. This model generates 480p videos from descriptions alone while allowing you to apply custom LoRA adapters for unique styles, characters, and effects — perfect for stylized content and rapid creative iteration.
Looking for higher resolution? Try Wan 2.2 T2V 720p LoRA for HD output with LoRA support.
Why It Looks Great
- Pure text-to-video: Generate complete videos from descriptions alone — no images needed.
- LoRA support: Apply up to 3 custom LoRAs each for standard, high-noise, and low-noise stages.
- Landscape & portrait: Supports both horizontal and vertical orientations for any platform.
- 480p efficiency: Ideal resolution for mobile content and rapid iteration.
- Negative prompt support: Exclude unwanted elements for precise control.
- Prompt Enhancer: Built-in tool to refine your descriptions automatically.
- Safety Checker: Optional content filtering for appropriate output.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the scene, action, and atmosphere you want. |
| negative_prompt | No | Elements to avoid in the generated video. |
| size | No | Output dimensions: 832×480 (landscape) or 480×832 (portrait). Default: 832×480. |
| duration | No | Video length: 5 or 8 seconds. Default: 5. |
| loras | No | Standard LoRA adapters to apply (up to 3). |
| high_noise_loras | No | LoRAs applied during high-noise denoising stages (up to 3). |
| low_noise_loras | No | LoRAs applied during low-noise denoising stages (up to 3). |
| seed | No | Random seed for reproducibility. Use -1 for random. |
| Enable Safety Checker | No | Toggle content safety filtering. |
How to Use
- Write your prompt — describe the scene, characters, motion, and atmosphere in detail.
- Use Prompt Enhancer (optional) — click to automatically enrich your description.
- Add negative prompt (optional) — specify elements to exclude.
- Choose size — select landscape (832×480) or portrait (480×832) orientation.
- Set duration — choose 5 or 8 seconds.
- Add LoRAs (optional) — click "+ Add Item" to include custom LoRA adapters.
- Set seed (optional) — for reproducible results.
- Run — click the button to generate.
- Download — preview and save your video.
Pricing
Per 5-second billing based on duration.
| Duration | Calculation | Cost |
|---|---|---|
| 5 seconds | 5 ÷ 5 × $0.20 | $0.20 |
| 8 seconds | 8 ÷ 5 × $0.20 | $0.32 |
Understanding LoRA Options
This model provides three different LoRA slots that affect different stages of the generation process:
| LoRA Type | When Applied | Best For | Max Count |
|---|---|---|---|
| loras | Throughout generation | General style, character consistency | 3 |
| high_noise_loras | Early denoising (high noise) | Overall composition, major style elements | 3 |
| low_noise_loras | Late denoising (low noise) | Fine details, textures, finishing touches | 3 |
Size Options
| Size | Orientation | Best For |
|---|---|---|
| 832×480 | Landscape | YouTube, presentations, desktop viewing |
| 480×832 | Portrait | TikTok, Instagram Reels, Stories, mobile |
Best Use Cases
- Stylized Content — Apply style LoRAs for unique visual aesthetics.
- Character Animation — Use character LoRAs for consistent identity in generated videos.
- Social Media Content — Create platform-optimized videos with custom styles.
- Rapid Style Testing — Experiment with different LoRA combinations affordably.
- Brand Content — Apply trained LoRAs for consistent brand visuals.
Example Prompts
- "A bride stands in a softly lit room, adjusting her earrings in the mirror. Her traditional dress is rich in detail—silk, embroidery, delicate patterns. The camera focuses on her calm yet nervous expression. Intimate, elegant, photorealistic portraiture with cultural depth."
- "Anime character walking through neon-lit city streets, rain falling, reflections on wet pavement"
- "Fantasy wizard casting spell, magical particles swirling, dramatic lighting, cinematic style"
- "Peaceful zen garden with flowing water, cherry blossoms falling, meditative atmosphere"
- "Cyberpunk motorcycle chase through futuristic city, motion blur, intense action"
How to Use LoRAs
For detailed guides on using and training custom LoRAs:
Pro Tips for Best Results
- Start without LoRAs to establish a baseline, then add them incrementally.
- Use high_noise_loras for major style/composition changes, low_noise_loras for subtle refinements.
- Match orientation to platform: portrait for TikTok/Reels, landscape for YouTube.
- Don't overload with LoRAs — sometimes 1-2 well-chosen LoRAs work better than many.
- Match your prompt language to the LoRA's training — use trigger words if applicable.
- 480p is perfect for testing LoRA combinations before upgrading to 720p.
Notes
- Duration options are 5 or 8 seconds only.
- Each LoRA slot supports up to 3 LoRAs.
- Enable Safety Checker for content that will be publicly shared.
- 480p is sufficient for most mobile viewing and social media platforms.
Wan 2.2 T2v 480p Lora API — Quick start
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/t2v-480p-lora with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Wan 2.2 T2v 480p Lora below.
HTTP example
# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/t2v-480p-lora" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "832*480",
"duration": 5,
"seed": -1
}'
# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# When status is "completed", read the output from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env
const result = await client.run("wavespeed-ai/wan-2.2/t2v-480p-lora", {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "832*480",
"duration": 5,
"seed": -1
});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"wavespeed-ai/wan-2.2/t2v-480p-lora",
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"negative_prompt": "blurry, low quality, distorted",
"size": "832*480",
"duration": 5,
"seed": -1
}
)
print(output["outputs"][0]) # → URL of the generated outputWan 2.2 T2v 480p Lora API — Frequently asked questions
What is the Wan 2.2 T2v 480p Lora API?
Wan 2.2 T2v 480p Lora is a WaveSpeedAI model for AI inference, exposed as a REST API on WaveSpeedAI. WAN 2.2 T2V 480p with LoRA generates text-to-video at 480p and supports custom LoRAs for personalized styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
How do I call the Wan 2.2 T2v 480p Lora API?
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.2-t2v-480p-lora.
How much does Wan 2.2 T2v 480p Lora cost per run?
Wan 2.2 T2v 480p Lora starts at $0.20 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
What inputs does Wan 2.2 T2v 480p Lora accept?
Key inputs: `prompt`, `duration`, `size`, `seed`, `negative_prompt`, `high_noise_loras`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-2.2-t2v-480p-lora.
How long does Wan 2.2 T2v 480p Lora take to generate?
Average end-to-end generation time on WaveSpeedAI is around 102 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.
Can I use Wan 2.2 T2v 480p Lora outputs commercially?
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.