lora-support
Wan 2.1 Text-to-Video 720P creates 720P videos from text prompts and supports custom LoRAs for personalized styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Input
Idle
Your request will cost $0.3 per run.
For $10 you can run this model approximately 33 times.
ExamplesView all
README
Wan 2.1 Text-to-Video 720p LoRA
Generate stunning videos from text descriptions with Wan 2.1 Text-to-Video 720p LoRA. This powerful model transforms your written prompts into high-quality 720p videos with smooth motion and cinematic quality — plus full LoRA support for custom styles, characters, and aesthetics.
Why It Stands Out
- Pure text-to-video generation: No source image needed — describe your vision and watch it come to life.
- LoRA support: Load custom LoRA models to apply specific styles, maintain character consistency, or match brand aesthetics.
- Prompt-guided creation: Control scenes, actions, camera movements, and atmosphere through natural language.
- Negative prompt support: Exclude unwanted elements for cleaner, more controlled outputs.
- Flexible duration: Generate 5-second or 10-second clips depending on your needs.
- Reproducibility: Use the seed parameter to recreate exact results or iterate on variations.
Pricing
| Duration | Price |
|---|---|
| 5 seconds | $0.30 |
| 10 seconds | $0.45 |
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text description of the video you want to generate. |
| negative_prompt | No | Elements to avoid in the generated video. |
| lora_url | No | URL to your custom LoRA model file. |
| lora_strength | No | LoRA influence strength (typically 0.5–1.0). |
| size | No | Output resolution (default: 1280×720). |
| num_inference_steps | No | Quality/speed trade-off (default: 30). |
| duration | No | Video length in seconds: 5 or 10 (default: 5). |
| guidance_scale | No | Prompt adherence strength (default: 5). |
| flow_shift | No | Motion intensity control (default: 5). |
| seed | No | Set for reproducibility; -1 for random. |
How to Use
- Write a prompt describing the scene, action, and style you want.
- Add a LoRA (optional) — paste the URL to your custom LoRA and set the strength.
- Set parameters — adjust duration, guidance scale, and other settings as needed.
- Add a negative prompt (optional) to exclude unwanted elements.
- Click Run and wait for your video to generate.
- Preview and download the result.
How to Use LoRA
LoRA (Low-Rank Adaptation) lets you customize the model's output style without retraining the full model.
- Use your LoRA: Host your .safetensors file at a public URL and paste it into the lora_url field.
- Train your LoRA: Learn how to create custom LoRAs in our guide: Train Your Own LoRA Model
Common LoRA use cases: consistent character appearance, specific art styles, brand-aligned aesthetics, anime/cartoon styles.
Best Use Cases
- Social Media Content — Create scroll-stopping video content from scratch.
- Marketing & Advertising — Produce concept videos and ad creatives without filming.
- Storytelling & Animation — Generate scenes for short films, music videos, or narrative projects.
- Game & App Development — Create promotional trailers and UI animations.
- Personalized Content — Use custom LoRAs for branded or character-consistent videos.
Pro Tips for Best Quality
- Be specific in your prompt — describe subject, action, environment, lighting, and camera movement.
- Use negative prompts to reduce common artifacts: blur, distortion, jitter, or watermarks.
- Start with lower inference steps (20–25) for quick previews, then increase for final renders.
- When using LoRA, start with strength around 0.7 and adjust based on results.
- Fix the seed when iterating to isolate the effect of parameter changes.
Notes
- Ensure any LoRA URLs are publicly accessible.
- Processing time varies based on duration and current queue load.
- Please ensure your prompts comply with content guidelines.